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
712
(712)
Pull requests
1.2k
(1.2k)
Discussions
Actions
Projects
Security and quality
Insights
More
items
[None][feat] Per View KV head transfer
- #20709
#20709
Merged
allisonlim-nv
merged 6 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
allisonlim-nv:feat/per-view-kv-head-transfer
allisonlim-nv/TensorRT-LLM:feat/per-view-kv-head-transfer
Copy head branch name to clipboard
Nov 3, 2026
Conversation
Commits
6
(6)
Checks
Files changed
Merged
[None][feat] Per View KV head transfer
#20709
allisonlim-nv
merged 6 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
allisonlim-nv:feat/per-view-kv-head-transfer
allisonlim-nv/TensorRT-LLM:feat/per-view-kv-head-transfer
Copy head branch name to clipboard
Commits
Commits on Nov 2, 2026
[None][feat] Reshard KV transfers using per-view attention heads
Show description for 293de1a
allisonlim-nv
committed
293de1a
View commit details
Copy full SHA for 293de1a
Browse repository at this point
Fix per-view KV transfer compatibility and bounce safety
Show description for ad1ca82
allisonlim-nv
committed
ad1ca82
View commit details
Copy full SHA for ad1ca82
Browse repository at this point
Fix per-view overlap caching across peer ranks
Show description for 29a4122
allisonlim-nv
committed
29a4122
View commit details
Copy full SHA for 29a4122
Browse repository at this point
Fix per-view partitions without explicit layer specs
Show description for 5801d0b
allisonlim-nv
committed
5801d0b
View commit details
Copy full SHA for 5801d0b
Browse repository at this point
Test per-view head mapping with larger generation TP
Show description for d73062e
allisonlim-nv
committed
d73062e
View commit details
Copy full SHA for d73062e
Browse repository at this point
Require per-view KV heads and resolve virtual layer geometry
Show description for adb01ef
allisonlim-nv
committed
adb01ef
View commit details
Copy full SHA for adb01ef
Browse repository at this point
You can’t perform that action at this time.
