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
900
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[None][fix] Guard MiniMax-M3 FP8 indexer against padded -1 cache slots
- #19113
#19113
Open
brb-nv
wants to merge 6 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
brb-nv:fix/minimax-m3-indexer-negative-slot-main
brb-nv/TensorRT-LLM:fix/minimax-m3-indexer-negative-slot-main
Copy head branch name to clipboard
Conversation
Commits
6
(6)
Checks
Files changed
Open
[None][fix] Guard MiniMax-M3 FP8 indexer against padded -1 cache slots
#19113
brb-nv
wants to merge 6 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
brb-nv:fix/minimax-m3-indexer-negative-slot-main
brb-nv/TensorRT-LLM:fix/minimax-m3-indexer-negative-slot-main
Copy head branch name to clipboard
Commits
Commits on Sep 23, 2026
[None][test] Cover the FP8 indexer's padded-slot guards
Show description for e8a045e
brb-nv
committed
e8a045e
View commit details
Copy full SHA for e8a045e
Browse repository at this point
[None][fix] Limit MiniMax-M3 decode kernels to the last real token
Show description for 9f4afa8
brb-nv
committed
9f4afa8
View commit details
Copy full SHA for 9f4afa8
Browse repository at this point
[None][fix] Reset the MSA cache-slot tail a piecewise step pads into
Show description for 55d6e78
brb-nv
committed
55d6e78
View commit details
Copy full SHA for 55d6e78
Browse repository at this point
[None][test] Cover the wiring of the MiniMax-M3 padding guards
Show description for 0f63888
brb-nv
committed
0f63888
View commit details
Copy full SHA for 0f63888
Browse repository at this point
Commits on Sep 24, 2026
fix test
Show description for 4795e08
brb-nv
committed
4795e08
View commit details
Copy full SHA for 4795e08
Browse repository at this point
Commits on Sep 25, 2026
fix another test
Show description for c522dff
brb-nv
committed
c522dff
View commit details
Copy full SHA for c522dff
Browse repository at this point
You can’t perform that action at this time.