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
754
(754)
Pull requests
1.4k
(1.4k)
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
1,350
(1,350)
Closed
16,635
(16,635)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[None][fix] Default MiniMax-H3 to 50 inference steps
VisualGen
#22489
·
karljang
opened
Nov 17, 2026
Collaborator
·
4 tasks done
·
·
1
[https://nvbugs/6838022][fix] Restore B300 DeepSeek accuracy coverage
#22488
·
trtllm-agent
opened
Nov 17, 2026
Collaborator
·
·
1
[None][fix] Double-buffer update_ready in the KDA decomposed chain kernel (#22179 back-port)
#22487
·
zhaoyuanh-nvidia
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
[None][chore] Use 50 steps for MiniMax-H3 defaults and quality tests
VisualGen
#22486
·
yibinl-nvidia
opened
Nov 17, 2026
Collaborator
·
·
3
[TRTLLM-17168][chore] Report Muse Spark Open's architecture in telemetry
ci: full pre-merge approved
#22485
·
moraxu
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
7
[None][doc] Fix dead Dynamo Kubernetes guide link
#22484
·
farisbasha
opened
Nov 17, 2026
·
1 task done
·
·
1
[None][feat] Mooncake store chain mode: GPU -> host tier -> pool (2/2)
#22483
·
brb-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
[https://nvbugs/6944747][test] Skip unsupported INT8 Sage Ulysses cases on Rubin
VisualGen
#22482
·
daichu-nv
opened
Nov 17, 2026
Contributor
·
1 task done
·
·
1
[None][feat] KVCacheManagerV2: host-tier drop hook and lossless pinned ring (1/2)
#22481
·
brb-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
[https://nvbugs/7106236][fix] Prevent MegaMoE CuTeDSL TEP CUDA-graph warmup hangs
#22480
·
peihu-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
3
[https://nvbugs/7090784][fix] Keep MiniMax M3 dispatch reporting outside compiled graphs
#22479
·
peihu-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
3
[None][perf] Skip FlashInfer run validation on repeat QSA PrimTS launches
#22477
·
farazkh80
opened
Nov 17, 2026
Collaborator
·
·
3
[https://nvbugs/7109999][fix] Size kept KV pool extents to a bound pool rebalancing cannot outgrow
#22476
·
thorjohnsen
opened
Nov 17, 2026
Collaborator
·
3 tasks done
·
·
[https://nvbugs/7106563][fix] Load BF16 PLE tables and native NVFP4 MTP weights
Agent Code Review: Low Risk
#22473
·
trtllm-agent
opened
Nov 17, 2026
Collaborator
·
3 tasks done
·
·
15
[https://nvbugs/7099626][fix] Isolate FlashInfer workspaces for single-worker MPI pools
Agent Code Review: Low Risk
#22472
·
trtllm-agent
opened
Nov 17, 2026
Collaborator
·
·
5
[TRTLLM-16622][perf] DeepSeek-V4: disagg GEN receives the next requests' KV while the batch decodes
#22470
·
ziyixiong-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
7
[https://nvbugs/7100966][fix] Profile multimodal encoders before temporary KV allocation
Agent Code Review: High Risk
#22468
·
trtllm-agent
opened
Nov 17, 2026
Collaborator
·
·
8
[TRTLLM-16622][perf] DeepSeek-V4.1: CSA2 attention-TP decode: Reuse layers load their source's decoded main rows
#22466
·
ziyixiong-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
[TRTLLM-16622][perf] DeepSeek-V4.1: CSA2 attention-TP decode: prefetch a Reindex layer's candidate blocks into L2
#22465
·
ziyixiong-nv
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
[TRTLLM-17978][perf] Reduce Gemma3 image-prefill peak memory with compact masks
#22463
·
zhaoyangwang-nvidia
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
15
[#22461][feat] Honor dummy all-reduce in MegaMoE scheduling
#22462
·
qiaoxj07
opened
Nov 17, 2026
Collaborator
·
3 tasks done
·
·
1
13
[None][refactor] trtllm_modeling_v2: remove the tune stage
#22459
·
Wanli-Jiang
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
1
[https://nvbugs/7088367][test] Pin UCX_NET_DEVICES to lo in single-host disagg tests
Agent Code Review: Low Risk
#22458
·
chuangz0
opened
Nov 17, 2026
Collaborator
·
1 task done
·
·
13
[TRTLLM-17005][refactor] migrate attention workspace tests to a host sizing component
#22457
·
Funatiq
opened
Nov 17, 2026
Collaborator
·
1 task
·
·
2
[#22299][fix] Compute raw logprobs before penalties, embedding bias and token bans in TorchSampler
#22456
·
lori-ren
opened
Nov 17, 2026
Contributor
·
1 task done
·
·
1
Previous
1
2
3
4
5
6
7
…
40
Next
You can’t perform that action at this time.