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
704
(704)
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
1,196
(1,196)
Closed
15,964
(15,964)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[https://nvbugs/6818710][fix] Port the update_helix_param base-hook guard to main
#21583
·
brnguyen2
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
2
[TRTLLM-16624][fix] Fix Helix MLA decode kernel selection
#21582
·
zhaoyuanh-nvidia
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
4
[None][perf] K3 DSpark drafter: opt-in CuTe DSL split-KV block attention
#21581
·
vsabavat
opened
Nov 3, 2026
Collaborator
·
2 tasks done
·
·
[None][perf] Muse Spark Open modeling_v2 TEP target: Vera Rubin low-latency levers and trtllm::fp4_block_scale_moe_prerouted
#21580
·
Tabrizian
opened
Nov 3, 2026
Member
·
1 task done
·
·
2
[#21577][fix] Completions logprobs: put each text_offset where its token starts
Community want to contribute
#21578
·
paolo-perrone
opened
Nov 3, 2026
·
1 task done
·
·
1
3
[None][feat] WinoVae: an optimized Wan 2.2 VAE (fused norms, Winograd convs, spatial sharding)
VisualGen
#21576
·
ishovkun
opened
Nov 3, 2026
Contributor
·
1 task done
·
·
7
[TRTLLM-17267][refactor] Move the embeddings, mm_encoder and tokenize handlers into serving classes
VisualGen
#21575
·
JunyiXu-nv
opened
Nov 3, 2026
Collaborator
·
·
[#21573][fix] MiniMax-M3 tool parser: release the text still buffered when a stream ends
Community want to contribute
#21574
·
paolo-perrone
opened
Nov 3, 2026
·
1 task done
·
·
1
1
[None][feat] Load nvidia/Cosmos3-Edge-FP8 with its W8A8/W8A16 step policy
VisualGen
#21572
·
ConstBob
opened
Nov 3, 2026
Contributor
·
1 task done
·
·
8
[None][doc] Add Hyperdrive configs for Nemotron 3.5 Super VL on B200 and B300
Community want to contribute
#21570
·
jvpflum
opened
Nov 3, 2026
·
1 task done
·
·
1
[#21462][fix] DFlash: resume a prefix-cache hit from a kept drafter slot on the dense arena
Community want to contribute
#21569
·
jvpflum
opened
Nov 3, 2026
·
1 task done
·
·
1
1
[#21460][perf] Skip no-op guided-decoding work in eager steps without guided requests
Community want to contribute
#21568
·
jvpflum
opened
Nov 3, 2026
·
1 task done
·
·
1
3
[TRTLLM-17264][refactor] Claim VisualGen in CBTS and add the serve import-isolation test
VisualGen
#21567
·
JunyiXu-nv
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
[TRTLLM-17269][refactor] Add per-dialect error renderers in serve/exception_handling
#21566
·
JunyiXu-nv
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
[None][feat] Add LPIPS video generation evaluation
VisualGen
#21564
·
yibinl-nvidia
opened
Nov 3, 2026
Collaborator
·
2 of 3 tasks
·
·
[None][infra] Waive 2 failed cases for main in pre-merge 67869
ci: full pre-merge approved
#21563
·
trtllm-agent
opened
Nov 3, 2026
Collaborator
·
·
5
[https://nvbugs/7030393][fix] Elide redundant async Ulysses copies
VisualGen
#21558
·
trtllm-agent
opened
Nov 3, 2026
Collaborator
·
·
4
[TRTLLM-17269][refactor] Extract the shared HTTP app assembly into serve/_base/app_builder.py
#21556
·
JunyiXu-nv
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
[None][feat] Support RocketKV sparse attention with KV cache manager V2
#21555
·
yizhang-nv
opened
Nov 3, 2026
Member
·
1 task done
·
·
2
[None][feat] Support skip softmax with KV cache manager V2
#21553
·
yizhang-nv
opened
Nov 3, 2026
Member
·
1 task done
·
·
4
[TRTLLM-17264][refactor] Move the VisualGen handlers into serve/api/visual_gen
VisualGen
#21552
·
JunyiXu-nv
opened
Nov 3, 2026
Collaborator
·
·
[TRTLLM-17263][refactor] Converge the three Anthropic orchestrations into one serving class
#21551
·
JunyiXu-nv
opened
Nov 3, 2026
Collaborator
·
·
[None][perf] MiniMax-H3: GEMM-epilogue and fused-norm kernels, faster decode and encode
VisualGen
#21549
·
luyiyun1021
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
11
[None][refactor] Mistral Large 4: own the checkpoint weight loader and mapper
#21548
·
yizhang-nv
opened
Nov 3, 2026
Member
·
1 task
·
·
[https://nvbugs/7023194][fix] Restore auxiliary KV pool selection for DSA FMHA
#21547
·
Hudayday
opened
Nov 3, 2026
Collaborator
·
1 task done
·
·
8
Previous
1
2
3
4
5
6
7
…
40
Next
You can’t perform that action at this time.