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
753
(753)
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
1,335
(1,335)
Closed
16,739
(16,739)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[None][test] Follow the hybrid cache refactor in the Qwen3.8-Flash-Next FP8 tests
#22580
·
yuxianq
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
1
[None][perf] Read ahead only the checkpoint bytes a node's ranks load under EP and PP
#22579
·
anish-shanbhag
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
[TRTLLM-17586][feat] Enable block reuse under aggregated Helix, including KDA recurrent state
#22577
·
asfiyab-nvidia
opened
Nov 18, 2026
Contributor
·
1 task done
·
·
3
[TRTLLM-16624][fix] Compile the multi-row gated RMSNorm kernel's batch-dependent variants up front
#22576
·
zhaoyuanh-nvidia
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
5
[None][test] Cover assistant tool calls on the first disaggregated chat request
#22575
·
joyang-nv
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
[None][chore] Update NCCL EP to 0.3.0
#22574
·
nv-lschneider
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
5
[#21479][test] Cover tool schema rendering across disaggregated chat forwarding
#22573
·
joyang-nv
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
[https://nvbugs/7088444][fix] Correct DeepSeek-V4-Pro four-GPU memory gate
Agent Code Review: Low Risk
#22572
·
trtllm-agent
opened
Nov 18, 2026
Collaborator
·
2 tasks done
·
·
15
[https://nvbugs/7113529][fix] Bucket the row counts of eager low-M MMA GEMMs
Agent Code Review: High Risk
#22571
·
chenfeiz0326
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
18
[None][test] Fix the Kimi K3 KDA metadata tests on main
#22570
·
VALLIS-NERIA
opened
Nov 18, 2026
Collaborator
·
·
6
[https://nvbugs/7099626][fix] Isolate single-worker FlashInfer workspaces and share JIT builds in the Qwen3-32B-FP8 disagg test
Agent Code Review: Low Risk
#22569
·
yuxianq
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
17
[None][perf] Keep no speculative recurrent state on hybrid disaggregated context servers
#22568
·
VALLIS-NERIA
opened
Nov 18, 2026
Collaborator
·
·
6
[https://nvbugs/7114472][infra] Waive 2 failed case(s) on DGX_B200+DGX_B300
Agent Code Review: Low Risk
auto-waive
ci: full pre-merge approved
#22567
·
trtllm-agent
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
6
[None][feat] Store Mooncake pool pages through the KV cache's cold-page codec
#22566
·
lfr-0531
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
[None][test] Enable nvMatmulHeuristics in long-running Blackwell and Rubin functional tests
#22565
·
peaceh-nv
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
6
[TRTLLM-18039][fix] Preserve shared-storage parameter views during GMS migration
#22563
·
zhaoyangwang-nvidia
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
9
[None][perf] KV cache manager v2: map GPU pools from larger physical chunks (TLLM_KV_CACHE_MANAGER_V2_GPU_CHUNK_MB)
#22562
·
roborluo
opened
Nov 18, 2026
Contributor
·
6 tasks done
·
·
[https://nvbugs/7081623][fix] Key attached multimodal embeddings for KV cache reuse
Agent Code Review: Low Risk
#22561
·
richardc-nv
opened
Nov 18, 2026
·
1 task done
·
·
32
[TRTLLMINF-459][fix] correct Slurm retry gating and wget output handling
#22560
·
hanjingtian
opened
Nov 18, 2026
Collaborator
·
1 task done
·
·
6
[None][perf] Qwen3.8-Flash-Next FP8 modeling_v2: CuTe verify index scores at MTP3 (opt-in)
#22559
·
Wanli-Jiang
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
[None][perf] KV cache manager v2 host tier: store only the live rows of compact QSA index pages
#22558
·
Wanli-Jiang
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
[None][perf] Qwen3.8-Flash-Next FP8 modeling_v2: compact QSA index pages (opt-in)
#22557
·
Wanli-Jiang
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
[None][perf] Qwen3.8-Flash-Next FP8 modeling_v2: four bitwise prefill-side kernel changes
#22556
·
Wanli-Jiang
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
[None][perf] QSA: compact index pages for the qwen4_exp cache manager (opt-in)
#22555
·
Wanli-Jiang
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
[None][feat] Qwen3.8-Flash-Next modeling_v2: serve sm_107 with the NVFP4 and FP8 targets
#22552
·
Wanli-Jiang
opened
Nov 18, 2026
Collaborator
·
1 task
·
·
Previous
1
2
3
4
5
6
7
…
40
Next
You can’t perform that action at this time.