OpenVINO Backend: Upgrade graph cache to use buffer pointers instead of names - #261
Draft
mostafafaheem wants to merge 36 commits into
Draft
OpenVINO Backend: Upgrade graph cache to use buffer pointers instead of names#261mostafafaheem wants to merge 36 commits into
mostafafaheem wants to merge 36 commits into
Conversation
…g_src to recorde the src ggml tensor for OpenVINO dynamic shape infer
enable qwen35 Fix after rebase remove logging
…t reason: the backend test initializes unary op inputs over a wide range, [-150, 150]. For FP32, exp(x) overflows around x ~= 88.7, so this test can randomly generate values right in or beyond the overflow region
In stateful mode the NEOX RoPE branch fed rank-3 data ([S, n_heads, head_size]) into the Multiply against the rank-4 cos/sin tables ([1, S, 1, n_dims/2]). That mixed-rank broadcast is miscomputed by the OpenVINO GPU plugin, corrupting the rotated Q/K and producing garbage output (e.g. Phi-3-mini). Lift the data to rank-4 before the split/ Multiply so the operands are equal-rank, matching what the TYPE_NORMAL branch already does. CPU and stateless paths are unaffected. Phi-3-mini-Q4_K_M, wiki.test perplexity, GPU stateful: before: PPL = 27120.43 after: PPL = 6.2263 (CPU reference: 6.2251)
…ov name in ov bk; 3) fix issue in arch test & op test with latest code update
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
…astpath-v2 fix for op regression due to is_model_splitted
mostafafaheem
marked this pull request as ready for review
July 22, 2026 19:12
mostafafaheem
marked this pull request as draft
July 23, 2026 17:50
wine99
force-pushed
the
dev_backend_openvino
branch
from
July 27, 2026 04:33
4250de7 to
175f422
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
This PR replaces using names for
graph_keystruct with buffer pointers+offsets. This was done due to the previous approach sometimes causing false negatives, where the first decode graph would be deemed a cache miss, even though it is the same as the prefill graph.Additional information
Example:
The views in the first decode graph accessed the
leaf_7andleaf_10tensors after they were named, whereas they were still unnamed when the prefill graph accessed them. This is purely a name difference, the underlying graph is the exact same.Requirements