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
608
Pull requests
899
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[TRTLLM-12807][feat] Wrap FP4 MLA as FMHA lib
- #15375
#15375
Closed
yuxianq
wants to merge 11 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
yuxianq:feat/trtllm-12807-fp4-mla-fmha-lib
yuxianq/TensorRT-LLM:feat/trtllm-12807-fp4-mla-fmha-lib
Copy head branch name to clipboard
Conversation
Commits
11
(11)
Checks
Files changed
Closed
[TRTLLM-12807][feat] Wrap FP4 MLA as FMHA lib
#15375
yuxianq
wants to merge 11 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
yuxianq:feat/trtllm-12807-fp4-mla-fmha-lib
yuxianq/TensorRT-LLM:feat/trtllm-12807-fp4-mla-fmha-lib
Copy head branch name to clipboard
Commits
Commits on Jun 20, 2026
[None][feat] Add high-precision KV pool support for FP4 MLA
Show description for 9743cf0
Tracin
authored and
yuxianq
committed
9743cf0
View commit details
Copy full SHA for 9743cf0
Browse repository at this point
[None][feat] Support NVFP4 MLA KV cache on FlashInfer
Show description for 7eec65c
Tracin
authored and
yuxianq
committed
7eec65c
View commit details
Copy full SHA for 7eec65c
Browse repository at this point
[None][feat] Add CuTile and CuTe DSL FP4 MLA decode backends
Show description for c5c2232
Tracin
authored and
yuxianq
committed
c5c2232
View commit details
Copy full SHA for c5c2232
Browse repository at this point
[None][test] Add FP4 MLA decode benchmark
Show description for c1006af
Tracin
authored and
yuxianq
committed
c1006af
View commit details
Copy full SHA for c1006af
Browse repository at this point
[None][fix] Force CUDA utility paths for FP4 MLA debugging
Show description for 5946c57
Tracin
authored and
yuxianq
committed
5946c57
View commit details
Copy full SHA for 5946c57
Browse repository at this point
Support FP4 MLA linear MTP
Show description for 2cb6f17
Tracin
authored and
yuxianq
committed
2cb6f17
View commit details
Copy full SHA for 2cb6f17
Browse repository at this point
Apply FP4 MLA v2 integration fixes
Show description for f6d19cd
Tracin
authored and
yuxianq
committed
f6d19cd
View commit details
Copy full SHA for f6d19cd
Browse repository at this point
Remove debug codes.
Show description for ebd1347
Tracin
authored and
yuxianq
committed
ebd1347
View commit details
Copy full SHA for ebd1347
Browse repository at this point
Fix MTP + CUDA graph.
Show description for 233176a
Tracin
authored and
yuxianq
committed
233176a
View commit details
Copy full SHA for 233176a
Browse repository at this point
[TRTLLM-12807][feat] Add TRTLLM FP4 MLA FMHA lib
Show description for a78bc11
yuxianq
committed
a78bc11
View commit details
Copy full SHA for a78bc11
Browse repository at this point
[TRTLLM-12807][fix] Fix PR gate checks
Show description for 3549726
yuxianq
committed
3549726
View commit details
Copy full SHA for 3549726
Browse repository at this point
You can’t perform that action at this time.
