Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
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
Public
Notifications
You must be signed in to change notification settings
Fork
2.8k
Star
14.8k
Code
Issues
611
Pull requests
945
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
All pull requests
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
945
(945)
Closed
14,595
(14,595)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
More items
Comfortable display density
Compact display density
[None][feat] modeling_v2 catalog: Kimi K3 single-GPU decode kernels as entries (sm_100)
#19833
·
vsabavat
opened
Oct 3, 2026
·
8 of 10 tasks
·
·
[None][feat] modeling_v2 catalog: Kimi K3 KDA and MLA decode kernels as stateful entries (sm_100)
#19832
·
vsabavat
opened
Oct 3, 2026
·
8 of 10 tasks
·
·
[None][fix] multi_stream_utils: record the calling stream on fn1's outputs
Community want to contribute
#19831
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[None][fix] kdaDecode legacy: __syncwarp before the lane-0 block-reduce stores
Community want to contribute
#19830
·
vsabavat
opened
Oct 2, 2026
·
7 of 10 tasks
·
·
[None][fix] Kimi K3 attn_res kernels: order the ws_stats reads and fence the slot releases
Community want to contribute
#19829
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[None][fix] MNNVL all-reduce: keep a grown workspace's predecessor alive for captured graphs
Community want to contribute
#19828
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[None][fix] DFlash: start the dummy slot at context length 0 every step
Community want to contribute
#19827
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[None][fix] Kimi K3 KDA prefill: K1 warps finish reading sPartialLast before the next chunk
Community want to contribute
#19826
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[None][perf] Enable tiled FP8 context FMHA for head_dim 256 on SM120
#19825
·
amukkara
opened
Oct 2, 2026
Collaborator
·
1 task done
·
·
1
[None][feat] RI-02 bind shared KV leases to lifecycle retirement
#19824
·
chienchunhung
opened
Oct 2, 2026
Collaborator
·
1 task done
·
·
2
[None][feat] RI-01 pin shared KV contracts and staging compatibility
#19823
·
chienchunhung
opened
Oct 2, 2026
Collaborator
·
1 task done
·
·
3
[None][chore] Share KV transfer lifecycle enforcement primitives
#19822
·
chienchunhung
opened
Oct 2, 2026
Collaborator
·
1 task done
·
·
4
[TRTLLM-16282][feat] Add sparse KV offload and GPU metadata publication
api-compatible
#19821
·
cascade812
opened
Oct 2, 2026
Collaborator
·
4 of 5 tasks
·
·
[TRTLLM-14620][feat] Add DSpark confidence verification policy
#19818
·
zhaoyuanh-nvidia
opened
Oct 2, 2026
Collaborator
·
5 of 7 tasks
·
·
4
[None][feat] KDA verify: optional per-token states in the V2 hybrid cache manager
Community want to contribute
#19817
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[None][perf] Cut host work between speculative decoding steps
Community want to contribute
#19816
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[https://nvbugs/6562942][fix] Load Qwen3.5 packed INT4 checkpoints
#19815
·
pranav-nvidia
opened
Oct 2, 2026
Contributor
·
1 task done
·
·
19
[None][feat] One-model speculative decoding: the worker produces the target logits
Community want to contribute
#19814
·
vsabavat
opened
Oct 2, 2026
·
8 of 10 tasks
·
·
[#19789][fix] Retract partial Mooncake master address publication
Community want to contribute
#19813
·
adenzhou1350
opened
Oct 2, 2026
·
2 of 3 tasks
·
·
1
1
[TRTLLM-16757][fix] Forward-port configuration model-list telemetry capture to main
ci: full pre-merge approved
#19811
·
Mgluhovskoi
opened
Oct 2, 2026
Collaborator
·
·
11
[https://nvbugs/6838021][test] Unwaive MiniMax-M3 MXFP8 piecewise CUDA graph test on B300
#19810
·
peihu-nv
opened
Oct 2, 2026
Collaborator
·
1 task done
·
·
7
[https://nvbugs/6838020][fix] Tolerate near-tie greedy flips in KV pool rebalance accuracy test
#19809
·
thorjohnsen
opened
Oct 2, 2026
Collaborator
·
1 task
·
·
1
[TRTLLM-16749][feat] Add MiniMax-H3 text encoder TP support
VisualGen
#19807
·
yibinl-nvidia
opened
Oct 2, 2026
Collaborator
·
1 task
·
·
[None][feat] Support non-gated FP8 block-scale MoE on SM121
Community want to contribute
#19806
·
Dorijan10
opened
Oct 2, 2026
Contributor
·
·
3
[None][fix] Release the cute wrappers of evicted KDA prefill scratch
Community want to contribute
#19804
·
bvolpato
opened
Oct 2, 2026
·
1 task
·
·
Previous
1
2
3
4
5
6
7
…
38
Next
You can’t perform that action at this time.