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
14.7k
Code
Issues
606
Pull requests
901
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[None][perf] Wire in custom decode kernels for MinimaxM3
- #18611
#18611
Merged
brb-nv
merged 8 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
brb-nv:user/brb/wire-in-custom-decode-kernels
brb-nv/TensorRT-LLM:user/brb/wire-in-custom-decode-kernels
Copy head branch name to clipboard
Sep 12, 2026
Conversation
Commits
8
(8)
Checks
Files changed
Merged
[None][perf] Wire in custom decode kernels for MinimaxM3
#18611
brb-nv
merged 8 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
brb-nv:user/brb/wire-in-custom-decode-kernels
brb-nv/TensorRT-LLM:user/brb/wire-in-custom-decode-kernels
Copy head branch name to clipboard
Commits
Commits on Sep 11, 2026
[None][perf] Wire in custom decode kernels for MinimaxM3
Show description for 28e5a16
brb-nv
committed
28e5a16
View commit details
Copy full SHA for 28e5a16
Browse repository at this point
minor fix
Show description for a68f737
brb-nv
committed
a68f737
View commit details
Copy full SHA for a68f737
Browse repository at this point
[None][chore] Write MSA step K/V in the phase that attends it
Show description for 7b4819c
brb-nv
committed
7b4819c
View commit details
Copy full SHA for 7b4819c
Browse repository at this point
[None][chore] Take MSA dense decode scratch from the shared workspace
Show description for 1c4d1b1
brb-nv
committed
1c4d1b1
View commit details
Copy full SHA for 1c4d1b1
Browse repository at this point
[None][chore] Say at the call site why M3 dense decode is not a fallback
Show description for 5b82855
brb-nv
committed
5b82855
View commit details
Copy full SHA for 5b82855
Browse repository at this point
[None][chore] Move the MSA kernels under the minimax_m3 package
Show description for ed1732f
brb-nv
committed
ed1732f
View commit details
Copy full SHA for ed1732f
Browse repository at this point
[None][chore] Reject a head count the sparse decode kernel cannot cover
Show description for 5b9372e
brb-nv
committed
5b9372e
View commit details
Copy full SHA for 5b9372e
Browse repository at this point
[None][chore] Reach the MSA kernels the way msa_sparse_gqa did
Show description for ee1ffa1
brb-nv
committed
ee1ffa1
View commit details
Copy full SHA for ee1ffa1
Browse repository at this point
You can’t perform that action at this time.