Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Events
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
NVIDIA
TensorRT-LLM
Repository navigation
Code
Issues
699
(699)
Pull requests
1.2k
(1.2k)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
75
(75)
Milestones
1
(1)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
1,160
(1,160)
Closed
15,823
(15,823)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[None][infra] Waive 1 failed cases for main in pre-merge 67464
ci: full pre-merge approved
#21398
·
trtllm-agent
opened
Nov 2, 2026
Collaborator
·
·
4
[TRTLLM-17163][test] Muse Spark Open stress settings and disagg cancellation marathon attach mode
#21397
·
moraxu
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
3
[None][fix] Enable the fused per-token AdaLN on SM103 (B300/GB300)
VisualGen
#21396
·
0z5a
opened
Nov 1, 2026
·
1 task done
·
·
1
[TRTLLM-17271][refactor] Stop trtllm-serve launchers from mutating caller-owned config dicts
api-compatible
#21394
·
JunyiXu-nv
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
17
[TRTLLM-17272][feat] Add public LLM health queries and a private-access lint for the serving frontends
#21393
·
JunyiXu-nv
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
16
[TRTLLM-17273][chore] Choose the trtllm-serve post-processing path once per server
api-compatible
#21392
·
JunyiXu-nv
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
7
[None][fix] Kimi-K3: honour the thinking and effort settings of Anthropic and chat requests
#21391
·
JunyiXu-nv
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
7
[None][docs] Rewrite Modeling V2 developer guides
#21390
·
litaotju
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
7
[TRTLLM-17273][chore] Read result completion through the public finished property in serve and scaffolding
#21389
·
JunyiXu-nv
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
7
[None][fix] Disaggregated Anthropic Messages: start the stream and ping while the context phase runs
#21388
·
JunyiXu-nv
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
16
[None][test] Remove 36 closed-bug waive entries for main
#21387
·
trtllm-agent
opened
Nov 1, 2026
Collaborator
·
·
[#21385][fix] Snapshot SWA per-layer KV staging inputs
#21386
·
peter941221
opened
Nov 1, 2026
Contributor
·
5 tasks done
·
·
1
6
[None][fix] Correctly select zsh in devcontainer
#21384
·
Funatiq
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
4
[None][fix] Release startup profiling KV cache before NIXL shutdown
#21382
·
dongfengy
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
1
[None][fix] Backport UCX timer-wheel fix for false UD timeouts
#21381
·
dongfengy
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
1
[None][feat] Staircase: Rubin GLM Optimized Low Latency (Conc up to 56)
#21380
·
dongfengy
opened
Nov 1, 2026
Collaborator
·
1 task done
·
·
12
[None][perf] skip scalar leaves in NCCL-window tensor collection
#21379
·
fredricz-20070104
opened
Nov 1, 2026
Collaborator
·
·
3
[None][feat] Muse Spark Open modeling_v2 TEP target: a per-deployment lever resolver and the Vera Rubin high-concurrency, mid-concurrency and low-latency fast paths
#21377
·
xwang233
opened
Oct 31, 2026
Collaborator
·
1 task done
·
·
6
[None][chore] Relax Modeling V2 naming and layout checks
#21376
·
litaotju
opened
Oct 31, 2026
Collaborator
·
1 task done
·
·
3
[TRTLLM-17527][refactor] transport typed Python request inputs
#21375
·
Funatiq
opened
Oct 31, 2026
Collaborator
·
1 task
·
·
12
[None][perf] HALO-Q: plan every EP above 8 in registers and repair only pairs that can move quota
#21373
·
JintaoPengCS
opened
Oct 31, 2026
Collaborator
·
1 task
·
·
5
[None][feat] Qwen3.8-Flash-Next NVFP4 modeling_v2 unified target on 4×GB300 (TP4/TEP4/ADP4), AgentX-tuned
#21372
·
Wanli-Jiang
opened
Oct 31, 2026
Collaborator
·
1 task
·
·
[https://nvbugs/7016340][test] Remove the MLA mixed-precision KV numeric test
#21371
·
Hudayday
opened
Oct 31, 2026
Collaborator
·
1 task done
·
·
5
[None][fix] Keep trailing letters in attribution source URLs
Community want to contribute
#21370
·
sarankumar1325
opened
Oct 31, 2026
·
1 task done
·
·
2
[https://nvbugs/6607482][ci] Print hang watchdog tracebacks to stderr
#21369
·
2ez4bz
opened
Oct 31, 2026
Collaborator
·
1 task done
·
·
13
Previous
1
2
3
4
5
6
7
…
40
Next
You can’t perform that action at this time.