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
Developer articles
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
749
(749)
Pull requests
1.3k
(1.3k)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
79
(79)
Milestones
1
(1)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
1,293
(1,293)
Closed
16,892
(16,892)
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] Test PR for the bot --commit check (do not merge)
#22696
·
wang0618
opened
Nov 20, 2026
·
·
1
[https://nvbugs/7036883][fix] Build FlashMLA for SM107-only targets
Agent Code Review: Low Risk
#22695
·
trtllm-agent
opened
Nov 20, 2026
Collaborator
·
2 tasks done
·
·
7
[None][perf] Enable qualified SM107 DeepSeek-V4.1 decode paths
#22694
·
liji-nv
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
27
[https://nvbugs/7126089][fix] Use scoped imports for KDA prefill references
Agent Code Review: Low Risk
ci: full pre-merge approved
#22693
·
trtllm-agent
opened
Nov 20, 2026
Collaborator
·
·
8
[#21891][perf] Allow prefill chunks to span multiple recurrent snapshot points
#22692
·
yu830
opened
Nov 20, 2026
·
1 task
·
·
18
[https://nvbugs/7117838][fix] Match GLM TEP4 routing to checkpoint layout
Agent Code Review: Low Risk
#22691
·
trtllm-agent
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
12
[None][fix] Fail pending and new RPC requests after the executor event loop crashes
#22690
·
lori-ren
opened
Nov 20, 2026
Contributor
·
1 task
·
·
[None][infra] Require --commit for bot commands on external PRs
#22688
·
weiminwang-nv
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
4
[TRTLLM-17529][refactor] separate response completion from resource release
#22687
·
Funatiq
opened
Nov 20, 2026
Collaborator
·
1 task
·
·
4
[https://nvbugs/7125691][fix] Restore the Kimi K3 KDA reference helpers used by test_kda_prefill.py
Agent Code Review: Low Risk
ci: full pre-merge approved
#22685
·
erictsai-nv
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
7
[TRTLLMINF-380][infra] Preserve Slurm diagnostic evidence for transient retries
#22683
·
hanjingtian
opened
Nov 20, 2026
Collaborator
·
1 task
·
·
1
[TRTLLM-17528][refactor] Improve response handling and regression coverage
#22682
·
Funatiq
opened
Nov 20, 2026
Collaborator
·
1 task
·
·
5
[https://nvbugs/7121545][infra] Split GB300-4_GPUs post-merge into 5 shards
Agent Code Review: Low Risk
ci: full pre-merge approved
#22680
·
yiqingy0
opened
Nov 20, 2026
Collaborator
·
1 task
·
·
12
[None][chore] Remove unused PuLP dependency
ci: full pre-merge approved
#22679
·
niukuo
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
5
[None][feat] specDSA: MXFP4 indexer K cache (DS-V4-Flash-FP4)
#22678
·
longcheng-nv
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
[TRTLLM-18117][fix] Release suffix automaton mask and staging buffers on shutdown
ci: full pre-merge approved
#22677
·
zhaoyangwang-nvidia
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
8
[None][feat] Wide-EP fault tolerance: MNNVL memory over a changing membership and MnnvlDist
#22676
·
arusli-nv
opened
Nov 20, 2026
Contributor
·
1 task done
·
·
11
[None][feat] Wide-EP fault tolerance: membership record, authority process and rendezvous store
#22675
·
arusli-nv
opened
Nov 20, 2026
Contributor
·
1 task done
·
·
11
[None][feat] EPLB: unbacked spare expert slots and expert restore into them
#22674
·
arusli-nv
opened
Nov 20, 2026
Contributor
·
1 task done
·
·
9
[TRTLLM-18125][feat] Publish trtllm-serve-config-guide to the NVIDIA skills catalog
#22672
·
kaiyux
opened
Nov 20, 2026
Member
·
1 task done
·
·
11
[None][feat] Autotuner: key cached tactics by the runner's source, so a code change re-tunes only the runners it touches
#22670
·
qiaoxj07
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
36
[None][fix] Key TRTLLM-Gen MoE tactics by EP layout, attention DP and dummy routing
#22668
·
ziyixiong-nv
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
15
[https://nvbugs/7123305][fix] Match NVFP4 layouts in sparse-offload accuracy
Agent Code Review: Low Risk
#22666
·
trtllm-agent
opened
Nov 20, 2026
Collaborator
·
·
7
[None][feat] Add trtllm-verify-change skill: run a change's declared tests at landing and delivery
#22665
·
yizhang-nv
opened
Nov 20, 2026
Member
·
2 tasks done
·
·
[None][perf] MegaMoE: run the SM107 gen-phase defaults on the decode scheduler
#22663
·
Barry-Delaney
opened
Nov 20, 2026
Collaborator
·
1 task done
·
·
Previous
1
2
3
4
5
6
7
…
40
Next
You can’t perform that action at this time.