From 75afe47c07e337e9592010cb67b079777515fd08 Mon Sep 17 00:00:00 2001 From: Chenguang Zheng Date: Wed, 4 Nov 2026 17:19:37 +0800 Subject: [PATCH 1/3] docs: anchor L1 weight demand against the checkpoint `methods/performance-ceiling-analysis` L1 divides a count by a rated peak and never revisits the model, so an error in the count reaches the floor unchallenged and no later roofline step re-examines it. The skill had no procedure for checking the demand side; `safetensors` appeared nowhere under this owner while the loading mechanics already lived next door. Add a two-gate prerequisite: the bidirectional per-tensor checkpoint join, and the separate per-rank weight ledger. The first needs no parallelism layout, so passing it certifies nothing about per-device bytes, and the distinction is stated rather than implied. State the blind spot too: the anchor covers the weight traffic term only, since a windowed and a global attention with equal head dimensions have byte-identical weights. Record the reviewed external source it derives from at a pinned commit, with per-file git blob and sha256 digests and per-file inspection scope. Documentation claims and source-verified claims are marked separately. Carry the source's two-threshold rule, which grants rejection authority only to a rated-peak bound and not to a per-operation roofline, and its archived guard-ablation study with the source's own limitations intact. What the source does not establish is recorded as explicitly as what it does: no end-to-end validation of predicted against measured serving performance within the inspected scope, unmeasured collectives upstream, and companion-blog corpus figures that the repository documents do not state and that must not be cited. `locally_verified` stays false; `empirical_validation` stays not_run. Refs: #348 Co-Authored-By: Claude Opus 5 --- docs/reference-matrix.md | 1 + .../performance-ceiling-analysis/SKILL.md | 53 +++++ .../metadata.json | 40 +++- .../huggingarch-checkpoint-anchor.md | 206 ++++++++++++++++++ .../huggingarch-source-identity.json | 137 ++++++++++++ 5 files changed, 429 insertions(+), 8 deletions(-) create mode 100644 src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md create mode 100644 src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json diff --git a/docs/reference-matrix.md b/docs/reference-matrix.md index 4be14b07c..6b477e835 100644 --- a/docs/reference-matrix.md +++ b/docs/reference-matrix.md @@ -254,6 +254,7 @@ SSD/OS systems columns. | arXiv 2608.01867 (CRISP) | search | critical-step classification | `optimization-search-policy` | | **A1 / Agent Skills** @ `69ef37e9424c0a7ea9dd2293b559e43ec8176379` | reference; Dot A-approved minimal consumption | Specification frontmatter/body/progressive disclosure and client guide catalog/activation/resource sections directly verified 2026-10-15; format guidance, not an execution permission grant | `src/inferrsi/skill_catalog.py`, existing CLI/arguments; metadata projection + explicit selection + resource resolution; no installer/router/client configuration | | **CR6 / Stas Bekman ML Engineering Open Book** @ `ee7517e0f562ff0e7d56c3e88c619d0c0c496ba7` (CC BY-SA 4.0 declared by source skill) | expert methodology | `skills/ml-engineering/SKILL.md` scoped principles, `skills/evaluate-cluster/SKILL.md` first 100 lines, targeted performance README MFU/HFU/NUMA/GC sections; scripts identified only, excluded storage/input/recovery lanes not mined | `training-resource-budget` + explicitly attributed/share-alike `references/stas-decision-notes.md`; Accelerator/RAM/Network/OS diagnosis and proposed verification, no local results | +| **shenh10/HuggingArch** @ `facbbbc96856e558b9084a94a5070b2e2c86cf0b` (MIT) | reference; mined for one prerequisite and one gating rule | Bidirectional checkpoint/tensor join and the separate per-rank weight ledger as an L1 demand-side prerequisite; the two-threshold rule separating a rated-peak bound that may refuse a measured row from a per-operation roofline that may only flag one; an analytical result whose cache identity omits measurement scope; archived guard-ablation study carried with the source's own limitations. Inspected 2026-11-04: 4 documents and 5 source files of a single-commit repository; **no end-to-end validation of predicted against measured serving performance exists in the inspected scope**, collectives are unmeasured upstream, and companion-blog corpus figures are explicitly unverified | `performance-ceiling-analysis`; [document](../src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md) + [identity](../src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json) | ### Reviewed paper methodology and cases diff --git a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md index fa34dcad4..6057a3857 100644 --- a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md +++ b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md @@ -29,6 +29,38 @@ Before profiling, gather what you can analytically: must be resolved via vendor documentation or an empirical measurement). 3. Existing benchmark numbers if available: throughput frames/s, TTFA p50/p95, RTF mean. Label their provenance (author-reported, local measurement, etc.). +4. For a checkpointed model, the checkpoint's own tensor headers, to anchor the + weight demand before any traffic figure is derived from it (below). + +### Anchor the weight demand before dividing by a peak + +L1 divides a count by a rated peak and never revisits the model, so an error in +the count propagates into the floor unchallenged: the formula is right, the +division is right, and the number is wrong. Where a checkpoint exists, the weight +half of that count has an external ground truth that needs a few header range +reads and no accelerator. Run **two** gates, in order: + +1. **Bidirectional per-tensor join.** Every header tensor must be claimed by + exactly one analytical leaf and agree with it in physical element count, and + every name the analysis stores must exist in the header. Report both + residuals: header tensors nothing claims, and stored names selecting nothing. + Treat a byte total as a checksum on this join, never as the primary gate — a + sum catches a wrong width but not two submodules swapped with the same total. + Compare bytes rather than elements wherever precision is mixed, because bytes + need no conversion when several formats share one file. +2. **Per-rank weight ledger.** The join needs no parallelism layout, so passing + it certifies nothing about per-device bytes. Before quoting any per-device or + per-degree figure, confirm every stored weight has a declared layout for each + stored axis and a format that gives it a width. Resolve a degree that does not + divide its dimension as declared; never substitute a divisor that divides. + +The anchor covers the **weight traffic term only**. A sliding-window and a global +attention with identical head dimensions have byte-identical weights, so KV +growth, boundedness and which nodes are cached are unanchored by it and carry +their own separate justification. Procedure, scope limits and the reviewed +external source: [checkpoint anchoring](references/huggingarch-checkpoint-anchor.md). +Loading mechanics stay with +[weight-loading-optimization](../weight-loading-optimization/SKILL.md). ## Three-level ceiling model @@ -125,6 +157,10 @@ Source: `hahnyuan/LLM-Viewer` @ 1893e4b5, `configs/DiT.py`, `model_params/DiT.py variation, mixed operation-class throughput or scheduling overhead. Changing the algorithm can change both work and traffic, so proximity to the old roof does not rule out improvement. +- L1's traffic term inherits every error in the counts it is handed, and no + later roofline step re-examines them. Anchor the weight half against the + checkpoint before reporting it; treat the KV half as unjustified until its + growth law is stated, since the weight anchor does not cover it. ### L2 — Empirical component ceiling @@ -356,3 +392,20 @@ prediction-based shortlist and [attention diagnosis](../../hardware/cuda/diagnos for algorithm/operation-class changes. These remain candidate guidance, not local performance measurements. The bundled helper only computes explicitly supplied L1 inputs under the contract above. + +### Reviewed external gate implementation + +[Checkpoint anchoring and the two-threshold rule](references/huggingarch-checkpoint-anchor.md) +records one external project's implemented separation between a bound that may +reject a result and an estimate that may not. A rated-peak capacity bound, +compared against the same measured row's own recorded peaks, refuses that row +outright; a per-operation roofline conditional on that operation's counts only +flags it, because a different legitimate implementation can change those counts. +Rejection authority tracks how invariant the bound is. The same document carries +that project's archived guard-ablation study, with its own stated limitations, as +external corroboration that an agent's self-assessment is not a verdict, and +states what the source does not establish — notably no end-to-end validation of +predicted against measured serving performance. Source identity and per-file +inspection scope: +[`huggingarch-source-identity.json`](references/huggingarch-source-identity.json). +Candidate guidance; no local measurement. diff --git a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json index 0a5e80627..68faec16f 100644 --- a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json +++ b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json @@ -68,12 +68,33 @@ ], "readset": "references/flexgen-offload-feasibility.md", "license": "CC-BY-4.0" + }, + { + "url": "https://github.com/shenh10/HuggingArch", + "commit": "facbbbc96856e558b9084a94a5070b2e2c86cf0b", + "paths": [ + "docs/validation.md", + "docs/measured_calibration.md", + "docs/evaluation_model.md", + "docs/known_limitations.md", + "backend/arch/validate/_matching.py", + "backend/arch/validate/_weight_ledger.py", + "backend/arch/validate/_ablation.py", + "backend/measure/scope.py", + "kernel_bench/emit.py" + ], + "type": "git", + "revision_precision": "full", + "license": "MIT", + "observed_at": "2026-11-04", + "identity": "references/huggingarch-source-identity.json", + "note": "Single-commit repository created 2026-11-03; no earlier revision exists to inspect. A companion blog post is recorded in the identity file as a partially read live URL with no snapshot, and two figures attributed to it are explicitly unverified." } ], "verification": { "locally_verified": false, "evidence_level": "source_grounded", - "note": "Historical repository methods plus reviewed paper extensions: references/papers-20261015/READSET.md records exact paper versions and inspection scope. Physical/conditional bounds, observed envelopes, simulator predictions and application measurements remain distinct. The bundled pure helper computes supplied L1 counts only; no automatic workload estimation, local accelerator measurements or E2E qualification." + "note": "Historical repository methods plus reviewed paper extensions: references/papers-20261015/READSET.md records exact paper versions and inspection scope. Physical/conditional bounds, observed envelopes, simulator predictions and application measurements remain distinct. The bundled pure helper computes supplied L1 counts only; no automatic workload estimation, local accelerator measurements or E2E qualification. The checkpoint-anchor prerequisite is derived from a reviewed external implementation at a pinned commit (references/huggingarch-checkpoint-anchor.md, identity in references/huggingarch-source-identity.json); documentation claims and source-verified claims are marked separately there. It anchors the weight demand term only and establishes nothing about KV counts, per-rank bytes without its second gate, or end-to-end serving performance." }, "applicability": { "scope": "inference serving systems (LLM, diffusion, audio)", @@ -96,27 +117,30 @@ "limitations": [ "Source-derived candidate; no local efficacy validation.", "Mooncake's prefix-reuse condition is an analytical approximation; current cache validity, placement, effective rates, overlap and SLO outcomes remain unverified.", - "FlexGen's cross-tier feasibility comparison assumes fitted rates and perfect overlap; relaxed placements may OOM, the printed bls wording remains unresolved, and current compatibility, latency and efficacy are unverified." + "FlexGen's cross-tier feasibility comparison assumes fitted rates and perfect overlap; relaxed placements may OOM, the printed bls wording remains unresolved, and current compatibility, latency and efficacy are unverified.", + "The checkpoint anchor covers analytical weight demand only; KV traffic, per-rank placement and end-to-end serving performance remain unanchored by it." ], "provenance_readsets": [ "references/flexgen-offload-feasibility.md", + "references/huggingarch-checkpoint-anchor.md", + "references/huggingarch-source-identity.json", "references/mooncake-prefix-reuse-feasibility.md", - "references/papers-20261015/cases/decision-cases.md", - "references/papers-20261015/govern-optimization-experiments/procedure.md", - "references/papers-20261015/govern-optimization-experiments/references/source-notes.md", "references/papers-20261015/INTEGRATION_NOTES.md", - "references/papers-20261015/knowledge/bounds-predictions-and-decisions.md", "references/papers-20261015/MECHANISMS.md", "references/papers-20261015/README.md", "references/papers-20261015/READSET.md", + "references/papers-20261015/STATIC_CHECKS.md", + "references/papers-20261015/cases/decision-cases.md", + "references/papers-20261015/govern-optimization-experiments/procedure.md", + "references/papers-20261015/govern-optimization-experiments/references/source-notes.md", + "references/papers-20261015/knowledge/bounds-predictions-and-decisions.md", "references/papers-20261015/redirect-cross-layer-optimization/procedure.md", "references/papers-20261015/redirect-cross-layer-optimization/references/source-notes.md", "references/papers-20261015/references/agentic-kernel.md", "references/papers-20261015/references/flashvector.md", "references/papers-20261015/references/inferencebench.md", "references/papers-20261015/references/prior-coverage.md", - "references/papers-20261015/references/vidur.md", - "references/papers-20261015/STATIC_CHECKS.md" + "references/papers-20261015/references/vidur.md" ], "consumption_mode": "packaged" } diff --git a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md new file mode 100644 index 000000000..4e3161366 --- /dev/null +++ b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md @@ -0,0 +1,206 @@ +# Anchoring analytical weight demand against the checkpoint + +Status: candidate; `empirical_validation: not_run`. This is a reviewed external +source, read at one pinned commit, recorded in +[`huggingarch-source-identity.json`](huggingarch-source-identity.json). It adds a +**prerequisite check** to the L1 analytical ceiling. It adds no ceiling level, no +bound, and no measurement. Claims below are marked `[code]` where they were +verified against the source files at that commit and `[doc]` where only the +project's own documentation states them. + +## Why L1 needs this + +L1 divides a work or traffic count by a rated peak. Nothing in the roofline +revisits the model afterwards, so an error in the count propagates into the floor +unchallenged and survives every later consistency check. The failure is quiet: +the formula is right, the division is right, and the number is wrong. + +For a checkpointed model the weight half of that count has an external +ground truth — the checkpoint's own tensor headers — that costs two or three +HTTP range reads and no accelerator. Use it before reporting any L1 traffic +figure derived from a parameter count. + +## The anchor is two gates, not one + +### Gate 1 — the bidirectional per-tensor join + +Join the analytical tensor inventory to the checkpoint header **in both +directions**, on the full tensor name `[code]`: + +- every header tensor must be claimed by exactly one analytical leaf and agree + with it in physical element count; +- every name the analysis stores must exist in the header. + +Both residuals are results, not diagnostics: header tensors nothing claims +(typically a forgotten router gate or expert bias) and stored names selecting +nothing. Header names are taken verbatim; the analysis side composes its names +from declared root, stack and module segments `[code]`. + +Storage bytes are a **checksum on that join, not the primary gate** `[doc]`. +The source's stated reason is worth carrying, because it is the failure a byte +total cannot see: + +> A sum catches a wrong width but not two submodules swapped with the same +> total, which is why it is secondary. + +Compare **bytes, not elements**, wherever precision is mixed: bytes are the only +unit needing no conversion when FP4 routed experts, FP8 attention and BF16 norms +share one file. An element total is reliable only for a single-precision +checkpoint `[doc]`. + +### Gate 2 — the per-rank weight ledger must build + +Gate 1 reads the checkpoint join, **which needs no parallelism layout at all** +`[code]`. So an inventory can pass Gate 1 and still be unpriceable per device: +every stored weight needs a declared layout for each stored axis and a format +that gives it a width, or no per-rank byte figure exists for it. + +The consequence for this skill is the part to remember: **passing a +model-level byte anchor certifies nothing about per-rank weight bytes.** Any L1 +figure quoted per device, or under a parallelism degree, needs Gate 2 as well. +A degree that does not divide its dimension must be resolved as declared — +refused, co-owned or padded — and never silently rewritten to a divisor that +divides `[doc]`. + +## What the weight anchor does not anchor + +The scope statement matters more than the gate, because the gate is persuasive +enough to be over-trusted. In the source's words `[doc]`: + +> The byte anchor sees everything written to disk and nothing about use at +> inference time: how many past positions a query attends to, whether a cache is +> bounded, which nodes are cached. A sliding-window attention and a global +> attention with the same head dimensions have byte-identical weights. + +So the anchor covers the **weight traffic term only**. The KV traffic term — the +term that dominates decode, and the one whose growth law decides whether a long +context is affordable — is entirely unanchored by it. A windowed layer wired as +dense caches the whole sequence and nothing in the parameter count reveals it. +The source gates that blind spot separately, through cache-growth laws judged +by substituting `s_kv → ∞` into the stored-length expression `[doc]`; its +ablation levers name the gating sliding-window contract after a real +`128TB` cache-size bug `[code]`. + +Treat KV counts as carrying their own, separate justification. Do not let a +clean weight anchor imply a clean traffic model. + +## Which bound may reject a measurement: the two-threshold rule + +This source applies **two different thresholds to the same measured row**, and +grants rejection authority to only one of them. It is an implemented instance of +the distinction in +[bounds, predictions and decisions](papers-20261015/knowledge/bounds-predictions-and-decisions.md) +between a conditional physical bound and an attainable envelope. + +| Threshold | Compared against | Authority | +|---|---|---| +| Achieved compute or bandwidth exceeds the card's rated peak | the peak **the row itself recorded at test time** | Row **refused at ingest** (HTTP 422) `[code]` | +| Measured time faster than the op's roofline estimate | an estimate conditional on that op's counts | Row **kept and reported**, carrying an anomaly badge `[doc]` | + +The ceiling constant is exactly `1.0` — the rated peak, with no tolerance +margin — and a row that records no peak passes, because the gate judges only +what the row itself states `[code]`. Its stated rationale: + +> A row may name the card's own peak, never beat it: a larger claimed rate is +> the signature of a numerator that does not describe the timed launch. + +The transferable rule: **rejection authority tracks how invariant the bound is.** +A rated-peak capacity bound, stated per resource and compared against the same +row's own recorded peaks, may reject a result outright — it cannot be beaten +without the numerator being wrong. A per-operation roofline conditional on a +particular set of counts may not, because a different but legitimate +implementation can change those counts. Flag it and re-derive; do not reject. + +## A theory result that no measurement can move + +The source keeps the analytical track's cache identity structurally independent +of all measurement state: the measurement scope contributes to a result's key +only when that result actually reads measurements `[code]`, so uploads, +promotions and rule changes cannot move a theory key `[doc]`. A measured time is +kept **beside** the roofline rather than replacing it, and a request may ask for +the analytical track alone `[doc]`. + +This is a useful implementation pattern for any frozen analytical reference: the +property is obtained from the key's construction, not from discipline about when +to recompute. + +## Archived guard-ablation study + +The source reports a study on whether each of its validation gates is necessary. +Carry it with its own header intact `[doc]`: + +> This section summarises an archived measurement. It was taken against an +> earlier validator revision, and its harness is not in the repository; the +> results are evidence for the design, not a verified property of the current +> gate set. + +Reported result: for three models, specs generated by an agent were 0 % valid +with all gates disabled and 100 % valid with all gates enabled. For one 1 T-parameter +MoE model the mean violation count fell from 32.7 storage (plus 7.3 naming, 4.3 +shape, 1.3 KV) to 0, and a 1.8 GB storage discrepancy to 0. Intermediate tiers +were **not monotone** for that model; only the endpoints were. + +Two details decide whether this is evidence or decoration: + +1. **The agent's own feedback channel was blinded too.** Disabling a gate drops + its findings from both the blocking error list and the per-gate warning + fields — "the two channels a guard acts on" `[code]`. Without that, an + ablation measures only the publish gate, not the agent's self-assessment. +2. **In the unguarded cells the agent exited reporting success**, with its own + (ablated) validation passing, while the full validator found the spec broken + `[doc]`. + +The source's own stated limitations: the fault injector targets attributes that +no longer exist, so its unique-coverage matrix is not reproducible without +migration; three seeds per cell give rates rather than single draws, with run-to-run +compute varying by about 12–16 %; the comparison against the committed spec is a +numeric and structural signature, not op-graph isomorphism; sandbox isolation +relied on de-contamination and a post-hoc scan rather than OS-level isolation; +and three models are not proof of completeness for every model or fault `[doc]`. + +Read against this repository's own rule that agent narrative is never a verdict, +this is independent corroboration from a project that measured the cost of +removing its gates. It is not a local result and establishes no local gate. + +## Facts this reference does not establish + +- **No end-to-end validation of predicted against measured serving performance.** + The inspected documents describe internal consistency (checkpoint anchoring, + algebraic invariants, per-operation numerics against a reference) and contain + no comparison of a predicted deployment figure to a measured one. The source's + own residual-risk section states that its per-operation axioms cannot verify + themselves without measurement `[doc]`. +- **Collective communication is not measured** in the source; its interconnect + term is analytical throughout `[doc]`. +- **Corpus scale is unverified.** The companion blog post cites figures for the + measured corpus that the inspected repository documents do not state. What the + documents do state is a registry of 361 providers over 124 signatures `[doc]`; + the six-figure numbers in the same documents are service request and memory + limits, not corpus size. The repository carries 16 provider environment files, + one of which is the reference framework `[code]`. Do not cite a corpus size. +- **The blog's quantitative examples are not attributable to this commit.** The + repository was created roughly four weeks after the post and carries a single + squashed commit, so no inspected revision corresponds to the state the post + describes. One figure the post reports about itself — a 2× error in a + long-context prefill baseline that halved a headline speedup — is recorded + here as blog-sourced and unverified, because it illustrates the tolerance and + provenance discipline this repository already requires. +- **No local qualification of any kind.** No accelerator was used; no InferRSI + campaign consumed this source. + +## Terminology hazard + +The source uses `Class A` through `Class E` for a **verification-rule** +taxonomy: per-operation cost axioms, conservation identities, perturbation +invariants, type contracts and dual-path cross-checks `[doc]`. That axis is +unrelated to any bound-versus-estimate distinction. When citing this source +alongside a discussion that also uses `Class A` / `Class B` labels, name the +taxonomy explicitly or use this repository's four evidence labels instead. + +## Readset and verification status + +Digests, blob identities and per-file inspection scope are in +[`huggingarch-source-identity.json`](huggingarch-source-identity.json). +`locally_verified` remains `false`. The documentation side was read in full for +the files listed; the companion blog post was read in part and is recorded with +that limit. diff --git a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json new file mode 100644 index 000000000..d9e9e7ad4 --- /dev/null +++ b/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json @@ -0,0 +1,137 @@ +{ + "schema_version": 1, + "subject": "HuggingArch checkpoint anchoring, two-threshold measurement gating and archived guard ablation", + "consumed_by": "huggingarch-checkpoint-anchor.md", + "required_resources": [ + "huggingarch-source-identity.json", + "huggingarch-checkpoint-anchor.md" + ], + "sources": [ + { + "type": "git", + "repository": "https://github.com/shenh10/HuggingArch", + "commit": "facbbbc96856e558b9084a94a5070b2e2c86cf0b", + "revision_precision": "full", + "commit_date": "2026-11-04T02:24:14Z", + "license": "MIT", + "observed_at": "2026-11-04", + "method": "GitHub API tree listing at the pinned commit for blob identity and size; raw file retrieval at the same commit, hashed locally. A complete file hash does not imply complete semantic inspection; per-file scope is stated below.", + "repository_history": { + "commits_on_default_branch": 1, + "first_commit_message": "init repo", + "repository_created_at": "2026-11-03T16:33:09Z", + "note": "A single squashed commit with no prior history. Figures published before this commit cannot be attributed to it, and no earlier revision is available for inspection." + }, + "files": [ + { + "path": "docs/validation.md", + "git_blob": "27ad32471db8c39937e04196a46fd3826a68def3", + "bytes": 37659, + "sha256": "917131e52bca569c9742efeba77606e2f102678acd9dccba06c593a833c9b800", + "inspection": "Sections 4-7 and 8-14 read; the checkpoint anchor, the facts weights do not anchor, the archived guard-ablation study with its limitations, the verification class taxonomy and the residual-risk statement." + }, + { + "path": "docs/measured_calibration.md", + "git_blob": "c48b065e2a7b765cb9bba5cdd5b6dd2e41a31f97", + "bytes": 54364, + "sha256": "7971fda4719590f64fc43e8207ad968ef130d714979200493a3479b2403ab60a", + "inspection": "Sections 1.1, 3.4, 3.5, 4.3 and 7.1-7.5 read; the measured envelope, version and coverage identity, provider and signature counts, the upload speed-of-light gate, lookup bounds, the three measurement outcomes, selection modes and result cache identity. Remaining sections not inspected." + }, + { + "path": "docs/evaluation_model.md", + "git_blob": "304eb9c8cd8ff7c27587bbe7042246f373d5f5e7", + "bytes": 13653, + "sha256": "a62578fbf17302e0bf6a85a7692d881ea6cd1ee19beed59202a80be1d330b53a", + "inspection": "Read in full; the layer-kind taxonomy and the stated reason traffic must be derived from a rewritten graph rather than summed over fused members." + }, + { + "path": "docs/known_limitations.md", + "git_blob": "4480f090cf338c4868832e6e25c34583e9085558", + "bytes": 29268, + "sha256": "0317f9edf17755bb58006130ed9fbfbabf4375d68d79fa744f811c7e9159172d", + "inspection": "Section headings read in full; bodies not inspected. Cited only for the heading-level fact that collective communication is not measured." + }, + { + "path": "backend/arch/validate/_matching.py", + "git_blob": "60b81c06768180b389e3aa820669f4e29807d228", + "bytes": 18640, + "sha256": "09adc8e4d1052e328c990526f90bafeca1c83eeaabac33d7167f4e71cf6a1a0b", + "inspection": "Module docstring and the join result structure read; both unmatched residuals are carried as data. Matching internals not traced." + }, + { + "path": "backend/arch/validate/_weight_ledger.py", + "git_blob": "22527d76c1325ab21e668a11c66afce469a3b1bd", + "bytes": 2161, + "sha256": "7fa7ded5928507bae4facaf64afda040e0f8d07530a225df894b6ecf3d49a8f9", + "inspection": "Read in full; the second gate and its stated independence from the layout-free checkpoint join." + }, + { + "path": "backend/measure/scope.py", + "git_blob": "34cd25765af8eba4d699d47a252c3a06b5bf1b00", + "bytes": 15337, + "sha256": "e409d0dd611ec412b8bd502f4a6dfcd7f68a1ffb8faeecd3695621f21ef31c84", + "inspection": "Result identity class read; the cache key omits the measurement scope when the result reads no measurements. Call sites not traced." + }, + { + "path": "kernel_bench/emit.py", + "git_blob": "55f30fc4edcbe8c38b992c78cb20812380258a7a", + "bytes": 39131, + "sha256": "dfaf576cb5f16680d51f4703d3f8b538fa934d15e6ea626871e2285710ef3d7a", + "inspection": "The utilization ceiling constant and the speed-of-light gate function read; the ceiling is 1.0 and a row recording no peak passes. Row construction not traced." + }, + { + "path": "backend/arch/validate/_ablation.py", + "git_blob": "be26c9952602ecdea9b8380f7a739420b036b69a", + "bytes": 3656, + "sha256": "865351ba04c9377aeed4a1ac3ccd998335e77aa3cefc69db08831b7cf3555edb", + "inspection": "Read in full; the lever vocabulary and the statement that a disabled lever is dropped from both the blocking error list and the per-gate warning fields." + }, + { + "path": "backend/arch/eval/checkpoint.py", + "git_blob": "88d9c402f694e166192d9df041275923f36deebe", + "bytes": 11273, + "sha256": "4128b47cf4998b93acebbfb62db02ac0c3e7ae1e9112cb7e85b5f4bb5ce8839f", + "inspection": "Pattern-scoped reading only; the join symbols named in the documentation are not in this file. Retained for digest completeness, not cited." + }, + { + "path": "docs/inference_cost_model.md", + "git_blob": "ebaed29491d49efbfa15c61a4cd6a3bd61f8d726", + "bytes": 45984, + "sha256": "1bdf615083e620ea22899fed41baa698fbb89cedf55db5b5e8d6fbcac9568372", + "inspection": "Retrieved and hashed; not inspected. Not cited." + }, + { + "path": "docs/README.md", + "git_blob": "c37d2a930d2e01d2b6d72e92d5900083fadd9c74", + "bytes": 6149, + "sha256": "9518dba944e780d5ce3c352a537bbf7450baae6d152fabc273f7628625f641f5", + "inspection": "Retrieved and hashed; not inspected. Not cited." + } + ], + "not_inspected": [ + "backend/ beyond the five files above", + "kernel_bench/ beyond emit.py", + "tests/, web/, supabase/, tools/, scripts/", + "docs/design.md, docs/parallelism.md, docs/kv_cache_storage.md, docs/attention_families.md, docs/auto_sweep.md, docs/deployment.md, docs/moe_expert_axis.md, docs/quantization.md, docs/symbolic_evaluation.md, docs/custom_models.md" + ] + }, + { + "type": "document", + "url": "https://shenhan.cc/zh/blog/huggingarch", + "published": "2026-10-08", + "observed_at": "2026-11-04", + "snapshot": "unknown", + "content_hash": "unknown", + "inspection": "Partial: approximately 81 percent of the page retrieved verbatim; the remainder reached only through a generated summary. Sections from 3.7 onward are therefore second-hand.", + "note": "No immutable snapshot was taken, so this is a live URL and not a frozen version. The post predates the repository commit above by roughly four weeks. Two figures attributed to this post in discussion - a measured-corpus row count with model and library counts, and a self-reported rate of agent self-approval under ablation - are not present in the inspected repository documents and are recorded as unverified. They must not be cited as source facts.", + "cited_for": "One self-reported quantitative error, labelled blog-sourced and unverified in the consuming document." + } + ], + "verification": { + "locally_verified": false, + "empirical_validation": "not_run", + "native_execution": "not_run", + "evidence_level": "source_grounded", + "note": "Documentation claims are separated from source-verified claims in the consuming document. No accelerator was used, no InferRSI campaign consumed this source, and the source's own reported study is an archived measurement against an earlier revision of its validator, with its harness absent from the repository." + } +} From 18c9a16c4634b793b4a0cd3f8a2beaab41ec0bef Mon Sep 17 00:00:00 2001 From: Chenguang Zheng Date: Wed, 4 Nov 2026 17:27:59 +0800 Subject: [PATCH 2/3] chore: refresh skill coverage view --- docs/skill-coverage.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/skill-coverage.md b/docs/skill-coverage.md index 50c3f1b6c..e2b7b1516 100644 --- a/docs/skill-coverage.md +++ b/docs/skill-coverage.md @@ -4,7 +4,7 @@ Generated from the registry, the skill sidecars and the two maintained matrices. **Do not edit by hand**; regenerate after any registry, skill, matrix or frozen-plan change. -- Input digest: `sha256:7640b171256091efd1514a33d5e434eef3feaed238fc92fe3eeba02fee94e9ff` +- Input digest: `sha256:c769760e582ddfc888c9c34a3a64e4ce4f806b49d67cfac7f1b56e7651e0d0d0` - Regenerate: `python tools/build_skill_coverage.py` - Verify without writing: `python tools/build_skill_coverage.py --check` @@ -135,7 +135,7 @@ optimization is fully covered or that any procedure has measured benefit. | [inference-optimization-casebook](../src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md) | common | How to structure and use a casebook of past optimization decisions as a decision-support tool. Extracts the casebook ... | Structuring and querying a casebook of past optimization decisions as decision support ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Optimize | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd) | candidate · not_run · 0 readset(s) | no-eval | | [kernel-writing-guide](../src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md) | common | Decision guide for writing custom inference kernels: when to write one, which framework to choose (Triton, CuTe DSL ... | Deciding whether to write a custom inference kernel, routing a kernel pattern to Triton ... | failure_modes, input_contract, produced_artifact, refusal_point
6 advice | 1 Accelerator · Optimize / Diagnose / Configure / Verify | 1 · Systems sources (Dao-AILab/causal-conv1d @ `cd81f0413cad2fc1e6f17e785ac39f59aae690cd` ...)
1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
1 · Systems sources (huggingface/transformers @ `0dad7b822255a0ae261ec45ae937371e859ffd1a` ...)
1 · Systems sources (mindspore-ai/akg @ `5aa15f3fe4d856eb60cd3b27447e04f5f1fb4dff` ...)
1 · Systems sources (sgl-project/sglang @ `16176278d0180f1a1a578e53e6eef432577876c2` ...)
1 · Systems sources (vllm-project/vllm @ `537a79f0fc5ba564d2bef43d54915b2f80f9f77d` (root ...) | candidate · not_run · 7 readset(s) | no-eval | | [optimization-search-policy](../src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md) | common | Policy for how an optimization agent should select, order, and stop optimization experiments. Covers candidate ... | Selecting, ordering and stopping optimization experiments: candidate generation ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Optimize | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
2 · Methodology and corpus references (RRSI — arXiv 2609.24972v3)
2 · Methodology and corpus references (arXiv 2608.01867 (CRISP))
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 9 readset(s) | no-eval | -| [performance-ceiling-analysis](../src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md) | common | Estimate optimization headroom before modifying an inference system. Produces a three-level ceiling model (analytical ... | inference serving systems (LLM, diffusion, audio) | — | 1 Accelerator · Diagnose / Verify
5 OS · Configure | 1 · Systems sources (FlexGen — [ICML 2023 / PMLR 202:31094–31116](https://proceedings.mlr.p ...)
1 · Systems sources (Mooncake — FAST '25 proceedings, pp. 155-170)
1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
1 · Systems sources (ebugger/Empirical-Roofline-Toolkit @ 0771fa9)
1 · Systems sources (hahnyuan/LLM-Viewer @ 1893e4b) | candidate · not_run · 18 readset(s) | no-eval | +| [performance-ceiling-analysis](../src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md) | common | Estimate optimization headroom before modifying an inference system. Produces a three-level ceiling model (analytical ... | inference serving systems (LLM, diffusion, audio) | — | 1 Accelerator · Diagnose / Verify
5 OS · Configure | 1 · Systems sources (FlexGen — [ICML 2023 / PMLR 202:31094–31116](https://proceedings.mlr.p ...)
1 · Systems sources (Mooncake — FAST '25 proceedings, pp. 155-170)
1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
1 · Systems sources (ebugger/Empirical-Roofline-Toolkit @ 0771fa9)
1 · Systems sources (hahnyuan/LLM-Viewer @ 1893e4b)
2 · Methodology and corpus references (shenh10/HuggingArch @ `facbbbc96856e558b9084a94a5070b2e2c86cf0b` ...) | candidate · not_run · 20 readset(s) | no-eval | | [plan-activation-residency](../src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md) | common | Propose training activation and gradient memory reductions by distinguishing lifetime reordering, address packing and ... | Proposing training activation and gradient memory reductions when pressure appears to ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | 1 Accelerator · Diagnose / Optimize / Verify | 1 · Systems sources (Checkmate — [1910.02653v3](https://arxiv.org/abs/1910.02653v3)) | candidate · not_run · 1 readset(s) | no-eval | | [repository-evolution-analysis](../src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md) | common | Analyze a repository's commit history to build a capability-evolution model: what the system can do, how it got there ... | any software repository with a recoverable git history | — | 5 OS · Diagnose / Configure / Verify | 2 · Methodology and corpus references (LearningToCommit/LearningToCommit @ 7e5a1d7)
2 · Methodology and corpus references (yetone/magpie @ 77800032) | candidate · not_run · 0 readset(s) | no-eval | | [skill-evolution-playbook](../src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md) | common | Practical design choices for evolving agent skills from execution traces: when one trajectory should update a skill ... | Design choices for evolving agent skills from execution traces, drawn from Trace2Skill ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | N/A: SKILL.md §§ When should one trajectory update a skill?, How large should a skill edit be?, and When should skills split or merge? govern skill-text evolution and held-out evaluation, not hardware-resource state or control. | 2 · Methodology and corpus references (Qwen-Applications/Trace2Skill @ 3d0b52a)
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 0 readset(s) | no-eval | From 1694a0b558c78f3920dc4f8667fee3b7c3b11c61 Mon Sep 17 00:00:00 2001 From: Chenguang Zheng Date: Wed, 4 Nov 2026 18:38:49 +0800 Subject: [PATCH 3/3] chore: regenerate skill index at the content commit The rebase kept only the coverage-view refresh, so the packaged records still pinned the previous main snapshot and the performance-ceiling-analysis projection was stale. Regenerate with `build_skill_index.py --source-revision 75afe47c07e337e9592010cb67b079777515fd08`. Apart from that skill's record, every record changes only its source pin. Agent-assisted-by: Claude Code / claude-opus-5-5 (author) Co-Authored-By: Claude Opus 5.5 Signed-off-by: Chenguang Zheng --- .../repo_packs/inferrsi/knowledge/README.md | 4 +- .../ascend-aclgraph-capture-replay.json | 4 +- .../ascend/skills/ascend-device-health.json | 4 +- .../skills/ascend-distributed-parallel.json | 4 +- .../ascend/skills/ascend-graph-mode.json | 4 +- .../skills/ascend-model-adaptation.json | 4 +- .../skills/ascend-operator-profiling.json | 4 +- .../ascend/skills/ascend-operator-tuning.json | 4 +- .../skills/ascend-optimization-casebook.json | 4 +- .../skills/ascend-performance-analysis.json | 4 +- .../ascend-video-diffusion-optimization.json | 4 +- .../ascend/skills/ascendc-tiling-design.json | 4 +- .../skills/cann-attribution-overlap.json | 4 +- .../knowledge/ascend/skills/torch-npu.json | 4 +- .../torchnpu-device-memory-lifecycle.json | 4 +- ...torchnpu-pinned-host-memory-lifecycle.json | 4 +- .../skills/assess-serving-preemption.json | 4 +- .../assess-split-backward-schedule.json | 4 +- .../skills/audit-fixed-workload-claim.json | 4 +- .../audit-h3-metal-fasth3-semantics.json | 4 +- .../skills/audit-h3-runtime-residency.json | 4 +- .../skills/audit-llama-runtime-state.json | 4 +- .../audit-recurrent-kv-finalization.json | 4 +- .../common/skills/audit-sd-cpp-residency.json | 4 +- .../audit-sglang-diffusion-lifetimes.json | 4 +- .../skills/audit-vllm-kv-lifetimes.json | 4 +- .../bound-windowed-attention-replay.json | 4 +- .../budget-speculative-verification.json | 4 +- .../skills/calibrate-serving-simulation.json | 4 +- .../skills/cgroup-resource-controls.json | 4 +- .../checkpoint-recovery-consistency.json | 4 +- .../skills/choose-parallel-training-plan.json | 4 +- .../skills/cite-check-downstream-pr.json | 4 +- .../common/skills/claim-contract.json | 4 +- .../knowledge/common/skills/comfy-ui.json | 4 +- .../common/skills/competitor-scan.json | 4 +- .../skills/dcp-async-save-performance.json | 4 +- .../skills/dense-performance-evidence.json | 4 +- .../diagnose-vllm-admission-pressure.json | 4 +- .../skills/diffusers-invocation-state.json | 4 +- .../common/skills/draft-acceptance-issue.json | 4 +- .../knowledge/common/skills/dwarfstar.json | 4 +- .../evaluate-elastic-serving-placement.json | 4 +- .../skills/generation-cache-lifecycle.json | 4 +- .../common/skills/host-memory-management.json | 4 +- .../skills/host-overhead-optimization.json | 4 +- .../knowledge/common/skills/husky.json | 4 +- .../skills/inference-benchmark-design.json | 4 +- .../inference-optimization-casebook.json | 4 +- .../common/skills/kernel-writing-guide.json | 4 +- .../common/skills/kv-tier-management.json | 4 +- .../lazy-evaluation-stream-lifetimes.json | 4 +- .../knowledge/common/skills/lily.json | 4 +- .../knowledge/common/skills/lithos-metal.json | 4 +- .../knowledge/common/skills/local-dream.json | 4 +- .../knowledge/common/skills/mistral-rs.json | 4 +- .../knowledge/common/skills/mlc-llm.json | 4 +- .../knowledge/common/skills/mlx-swift-lm.json | 4 +- .../common/skills/npu-skill-factory.json | 4 +- .../skills/optimization-search-policy.json | 4 +- .../common/skills/os-process-placement.json | 4 +- .../skills/performance-ceiling-analysis.json | 57 ++++++++++++++----- .../skills/plan-activation-residency.json | 4 +- .../knowledge/common/skills/project-maya.json | 4 +- .../knowledge/common/skills/pytorch.json | 4 +- .../skills/repository-evolution-analysis.json | 4 +- .../knowledge/common/skills/rsi-evidence.json | 4 +- .../skills/skill-evolution-playbook.json | 4 +- .../knowledge/common/skills/splash.json | 4 +- .../common/skills/storage-io-measurement.json | 4 +- .../skills/training-input-pipeline.json | 4 +- .../skills/training-resource-budget.json | 4 +- .../skills/video-diffusion-optimization.json | 4 +- .../knowledge/common/skills/vllm-metal.json | 4 +- .../skills/weight-loading-optimization.json | 4 +- .../cuda/skills/audit-afd-p2p-exchanges.json | 4 +- .../skills/audit-flare-session-lifecycle.json | 4 +- .../diagnose-attention-bottlenecks.json | 4 +- .../cuda/skills/host-overhead-profiling.json | 4 +- .../cuda/skills/reason-hopper-kernels.json | 4 +- 80 files changed, 201 insertions(+), 172 deletions(-) diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md index 86ee95d7e..b6df40d0b 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md @@ -15,7 +15,7 @@ These are knowledge abstracts (`--kind knowledge`), with namespaced package IDs distinct from explicitly selected `checkout_ref` skills. Ascend/CUDA procedures use their corresponding backend; shared methods use `common`. -Source snapshot: [7aa3344bf84c42467f43b3a927e1c7d13642bd55](https://github.com/InferMatrixLab/InferRSI/tree/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library). +Source snapshot: [75afe47c07e337e9592010cb67b079777515fd08](https://github.com/InferMatrixLab/InferRSI/tree/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library). ```bash inferrsi knowledge search 'profiling' --repo-type inferrsi --limit 50 @@ -29,7 +29,7 @@ contain the current input paths and bytes (Git checkout filters are respected). ```bash python tools/build_skill_index.py --source-revision -python tools/build_skill_index.py --source-revision 7aa3344bf84c42467f43b3a927e1c7d13642bd55 --check +python tools/build_skill_index.py --source-revision 75afe47c07e337e9592010cb67b079777515fd08 --check ``` `--check` detects missing, stale and unexpected generated records without writing. diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json index d628bdadd..7fe19c695 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json index f4b372d19..a4ae5a1f1 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json index 4b940539c..5e503c856 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json @@ -27,8 +27,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json index 5c1c8590b..3227b0035 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json index 971e9813a..74192e47f 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json index e8d595cbc..58e5bc1f6 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json index 64816a247..e995bc3f2 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json index 7521c9f69..168c1d3bf 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json index 2a4a0ace2..fb031cd73 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json index a2d677d4d..dc750b710 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json index ea618b662..42097b8ad 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json index ca740b5b7..6ace947aa 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json index 7c1cde5ed..e3a983a2f 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json @@ -20,8 +20,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md", "src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json index d6676b490..85b679618 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json index d6ea1871c..1ec8db293 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json index 12aeca1fd..3f3b811a7 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md", "src/inferrsi/data/skill_library/methods/assess-serving-preemption/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json index 7c6e81473..cac9d8029 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md", "src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json index a3b85ccdc..b40e79b6e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json @@ -20,8 +20,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md", "src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json index 50b90d31b..d20f4030e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/LICENSE", "src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json index c01e0e11f..aeace8c4d 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json @@ -30,8 +30,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/LICENSE", "src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json index 3adab00f6..dc8af9d52 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md", "src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json index d5ab3d293..b1f3a8576 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/LICENSE", "src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json index 8b883145a..2d250a1d2 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/LICENSE", "src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json index 2dab44411..939ef4c74 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/LICENSE", "src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json index a4074b797..608a9f410 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md", "src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json index 3c226dfe4..26c857a3a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md", "src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json index bb08f2ed5..5b04eada9 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md", "src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json index 3e86452fe..2937ba671 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md", "src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json index a88384b33..4412c73a5 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json index 3572a1f8c..8fe668ae2 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md", "src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json index d5ce0bdbf..5b9c62234 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md", "src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json index ded00b5e0..1e216610d 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json index a7f2bfa5d..b87cc84e5 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json index acdc57b97..77ac49e77 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/comfy-ui/LICENSE", "src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json index 0f5b0fb34..ea75836f6 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json index 064e2ca25..543951e78 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md", "src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json index b20edd811..edc827714 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md", "src/inferrsi/data/skill_library/methods/dense-performance-evidence/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json index 70fd8e8a5..c2ddd893a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md", "src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json index 3a883cf9a..506e4bccc 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md", "src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json index e90c2488d..de0b6b10a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json index c456f30e9..45d33fed8 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/dwarfstar/LICENSE", "src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json index 3482d1338..8e936da5f 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md", "src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json index 7d68adf8b..cc813836a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md", "src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json index bb39eac1d..2543821c5 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json @@ -30,8 +30,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/host-memory-management/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json index 9f20ba9d7..f9ef36252 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json index 3dee4b666..e54919a52 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/husky/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/husky/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/husky/SKILL.md", "src/inferrsi/data/skill_library/repositories/husky/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json index 3b2327374..dac11fcbb 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json @@ -35,8 +35,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json index 3d6372c43..960e96b55 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md", "src/inferrsi/data/skill_library/methods/inference-optimization-casebook/cases/admission-drain-occupancy.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json index 1040189df..9c0987a67 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json @@ -39,8 +39,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md", "src/inferrsi/data/skill_library/methods/kernel-writing-guide/cases/causal-conv1d-dispatch-state.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json index 1c1f0ac80..16f626d1e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md", "src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json index c3b8b61d3..16da6e72a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md", "src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json index 8c592e80d..32b648bfe 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lily/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/lily/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/lily/LICENSE", "src/inferrsi/data/skill_library/repositories/lily/NOTICE.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json index 26722f7f4..94af0eecc 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/lithos-metal/LICENSE", "src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json index cb94c8a24..79e36a9d4 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md", "src/inferrsi/data/skill_library/repositories/local-dream/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json index 636fbe213..ba24664d3 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/mistral-rs/LICENSE", "src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json index b94c5f561..676d631e3 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json @@ -27,8 +27,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/mlc-llm/LICENSE", "src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json index fef01f452..9423feed7 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json @@ -27,8 +27,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/mlx-swift-lm/LICENSE", "src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json index 1adcbdc00..0bc4bd558 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json index 8965fb642..00cf799cf 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md", "src/inferrsi/data/skill_library/methods/optimization-search-policy/cases/sarathi-chunk-budget.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json index 8c0cf7b12..248ad7c8b 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/os-process-placement/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json index ae1810d82..bebd6d29a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json @@ -22,12 +22,14 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/flexgen-offload-feasibility.md", + "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md", + "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/mooncake-prefix-reuse-feasibility.md", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/papers-20261015/INTEGRATION_NOTES.md", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/papers-20261015/MECHANISMS.md", @@ -50,7 +52,7 @@ "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/scripts/roofline.py", "src/inferrsi/data/skill_library/skill-index.json" ], - "content_sha256": "0203dfabd2a02d2ab8f8696b922dcc3df86b3a811352a5bc6cea57aee68e869c" + "content_sha256": "1f4af1f484b67d53b1377ff6282dffd1470bc08c861cbcea906167ceceb6f268" } ], "index_type": "packaged-skill", @@ -59,9 +61,11 @@ }, "checkout_ref": "checkout:performance-ceiling-analysis", "source_files": { - "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md": "0203dfabd2a02d2ab8f8696b922dcc3df86b3a811352a5bc6cea57aee68e869c", - "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json": "70cd45ab665d4a83544a55fb48f2c83f195715a39af1e8e238ab574403150212", + "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md": "1f4af1f484b67d53b1377ff6282dffd1470bc08c861cbcea906167ceceb6f268", + "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json": "dcd16d3a64a777d5f5c63e37a6335b40269119efbc2f32185df383cfa10d7b54", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/flexgen-offload-feasibility.md": "984cc41c4412eafa6d20e109dea8927ad321a668776bc86bbffda0a94dfa9cc7", + "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md": "ccaa32c42da6e81c9dba3fa10afe5caf07b6f64f2d01e8acbdda664d4cf34007", + "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/huggingarch-source-identity.json": "9ccf148682c30ed4f1a3f5cbf921bafd09f3ca446d89a7c36a5327481172d0fe", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/mooncake-prefix-reuse-feasibility.md": "e64b62fded4490708414a898f540b0319c54d2b205fd5d060acaab419734d100", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/papers-20261015/INTEGRATION_NOTES.md": "083e462e0a204dce599362d46712fcfb392d053c5cda56216e22e28d4b8fa0fa", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/references/papers-20261015/MECHANISMS.md": "742c249082ceca230326f4407a40130fe624553b796ae5a157a8a4c15a7e1398", @@ -156,12 +160,33 @@ ], "readset": "references/flexgen-offload-feasibility.md", "license": "CC-BY-4.0" + }, + { + "url": "https://github.com/shenh10/HuggingArch", + "commit": "facbbbc96856e558b9084a94a5070b2e2c86cf0b", + "paths": [ + "docs/validation.md", + "docs/measured_calibration.md", + "docs/evaluation_model.md", + "docs/known_limitations.md", + "backend/arch/validate/_matching.py", + "backend/arch/validate/_weight_ledger.py", + "backend/arch/validate/_ablation.py", + "backend/measure/scope.py", + "kernel_bench/emit.py" + ], + "type": "git", + "revision_precision": "full", + "license": "MIT", + "observed_at": "2026-11-04", + "identity": "references/huggingarch-source-identity.json", + "note": "Single-commit repository created 2026-11-03; no earlier revision exists to inspect. A companion blog post is recorded in the identity file as a partially read live URL with no snapshot, and two figures attributed to it are explicitly unverified." } ], "verification": { "locally_verified": false, "evidence_level": "source_grounded", - "note": "Historical repository methods plus reviewed paper extensions: references/papers-20261015/READSET.md records exact paper versions and inspection scope. Physical/conditional bounds, observed envelopes, simulator predictions and application measurements remain distinct. The bundled pure helper computes supplied L1 counts only; no automatic workload estimation, local accelerator measurements or E2E qualification." + "note": "Historical repository methods plus reviewed paper extensions: references/papers-20261015/READSET.md records exact paper versions and inspection scope. Physical/conditional bounds, observed envelopes, simulator predictions and application measurements remain distinct. The bundled pure helper computes supplied L1 counts only; no automatic workload estimation, local accelerator measurements or E2E qualification. The checkpoint-anchor prerequisite is derived from a reviewed external implementation at a pinned commit (references/huggingarch-checkpoint-anchor.md, identity in references/huggingarch-source-identity.json); documentation claims and source-verified claims are marked separately there. It anchors the weight demand term only and establishes nothing about KV counts, per-rank bytes without its second gate, or end-to-end serving performance." }, "applicability": { "scope": "inference serving systems (LLM, diffusion, audio)", @@ -184,27 +209,30 @@ "limitations": [ "Source-derived candidate; no local efficacy validation.", "Mooncake's prefix-reuse condition is an analytical approximation; current cache validity, placement, effective rates, overlap and SLO outcomes remain unverified.", - "FlexGen's cross-tier feasibility comparison assumes fitted rates and perfect overlap; relaxed placements may OOM, the printed bls wording remains unresolved, and current compatibility, latency and efficacy are unverified." + "FlexGen's cross-tier feasibility comparison assumes fitted rates and perfect overlap; relaxed placements may OOM, the printed bls wording remains unresolved, and current compatibility, latency and efficacy are unverified.", + "The checkpoint anchor covers analytical weight demand only; KV traffic, per-rank placement and end-to-end serving performance remain unanchored by it." ], "provenance_readsets": [ "references/flexgen-offload-feasibility.md", + "references/huggingarch-checkpoint-anchor.md", + "references/huggingarch-source-identity.json", "references/mooncake-prefix-reuse-feasibility.md", - "references/papers-20261015/cases/decision-cases.md", - "references/papers-20261015/govern-optimization-experiments/procedure.md", - "references/papers-20261015/govern-optimization-experiments/references/source-notes.md", "references/papers-20261015/INTEGRATION_NOTES.md", - "references/papers-20261015/knowledge/bounds-predictions-and-decisions.md", "references/papers-20261015/MECHANISMS.md", "references/papers-20261015/README.md", "references/papers-20261015/READSET.md", + "references/papers-20261015/STATIC_CHECKS.md", + "references/papers-20261015/cases/decision-cases.md", + "references/papers-20261015/govern-optimization-experiments/procedure.md", + "references/papers-20261015/govern-optimization-experiments/references/source-notes.md", + "references/papers-20261015/knowledge/bounds-predictions-and-decisions.md", "references/papers-20261015/redirect-cross-layer-optimization/procedure.md", "references/papers-20261015/redirect-cross-layer-optimization/references/source-notes.md", "references/papers-20261015/references/agentic-kernel.md", "references/papers-20261015/references/flashvector.md", "references/papers-20261015/references/inferencebench.md", "references/papers-20261015/references/prior-coverage.md", - "references/papers-20261015/references/vidur.md", - "references/papers-20261015/STATIC_CHECKS.md" + "references/papers-20261015/references/vidur.md" ], "consumption_mode": "packaged" }, @@ -224,7 +252,8 @@ "The backend categorizes the procedure's hardware dependency; it does not certify compatibility, and skills.discovery is a discovery scenario.", "Source-derived candidate; no local efficacy validation.", "Mooncake's prefix-reuse condition is an analytical approximation; current cache validity, placement, effective rates, overlap and SLO outcomes remain unverified.", - "FlexGen's cross-tier feasibility comparison assumes fitted rates and perfect overlap; relaxed placements may OOM, the printed bls wording remains unresolved, and current compatibility, latency and efficacy are unverified." + "FlexGen's cross-tier feasibility comparison assumes fitted rates and perfect overlap; relaxed placements may OOM, the printed bls wording remains unresolved, and current compatibility, latency and efficacy are unverified.", + "The checkpoint anchor covers analytical weight demand only; KV traffic, per-rank placement and end-to-end serving performance remain unanchored by it." ], "verification": { "locally_verified": false, diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json index 5ccb28ffe..b7f9d17aa 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md", "src/inferrsi/data/skill_library/methods/plan-activation-residency/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json index abec7ae74..878d0112e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/project-maya/LICENSE", "src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json index 97d160bec..667564c65 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/LICENSE", "src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json index 27968f7c8..28ee06f65 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md", "src/inferrsi/data/skill_library/methods/repository-evolution-analysis/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json index 465739baa..484f6c5d8 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json index c470e93b8..f9b7f9c86 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md", "src/inferrsi/data/skill_library/methods/skill-evolution-playbook/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json index a9476f7cf..a9a697547 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/splash/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/splash/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/splash/LICENSE", "src/inferrsi/data/skill_library/repositories/splash/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json index fc715e09f..64e472b91 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json index 045b18bc4..e92188ed4 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md", "src/inferrsi/data/skill_library/methods/training-input-pipeline/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json index a2429cac2..8b52ec1c7 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md", "src/inferrsi/data/skill_library/methods/training-resource-budget/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json index 2fbb6eebc..dc254ff1e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md", "src/inferrsi/data/skill_library/methods/video-diffusion-optimization/assets/campaign.template.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json index 179f342ea..5e3c9e7f4 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm-metal/LICENSE", "src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json index 3cc50bdee..898aaecee 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md", "src/inferrsi/data/skill_library/methods/weight-loading-optimization/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json index 42b227ef5..68ce34bcf 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md", "src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json index 0fc99822c..5772cbcd3 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/LICENSE", "src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json index 19f847d38..b3d4a6963 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md", "src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json index 7fac0bc38..bff1a8f11 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md", "src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json index 55040913f..03045b447 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json @@ -36,8 +36,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/75afe47c07e337e9592010cb67b079777515fd08/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md", + "commit": "75afe47c07e337e9592010cb67b079777515fd08", "paths": [ "src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md", "src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/metadata.json",