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
901
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[None][feat] Add KV cache manager V2 support for DSA
- #16060
#16060
Merged
yizhang-nv
merged 12 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
yizhang-nv:codex/dsa-kv-cache-v2-main
yizhang-nv/TensorRT-LLM:codex/dsa-kv-cache-v2-main
Copy head branch name to clipboard
Aug 11, 2026
Conversation
Commits
12
(12)
Checks
Files changed
Merged
[None][feat] Add KV cache manager V2 support for DSA
#16060
yizhang-nv
merged 12 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
yizhang-nv:codex/dsa-kv-cache-v2-main
yizhang-nv/TensorRT-LLM:codex/dsa-kv-cache-v2-main
Copy head branch name to clipboard
Commits
Commits on Aug 10, 2026
[None][feat] add DSA KV cache manager V2 support
Show description for 6a5aa93
yizhang-nv
committed
6a5aa93
View commit details
Copy full SHA for 6a5aa93
Browse repository at this point
[None][fix] resolve DSA indexer cache page indices
Show description for 032e7c8
yizhang-nv
committed
032e7c8
View commit details
Copy full SHA for 032e7c8
Browse repository at this point
[None][fix] stabilize DSA draft cache replay with V2
Show description for 24be8e5
yizhang-nv
committed
24be8e5
View commit details
Copy full SHA for 24be8e5
Browse repository at this point
[None][fix] pre-allocate DSA draft indexer buffers for CUDA graph replay
Show description for b89caba
erictsai-nv
authored and
yizhang-nv
committed
b89caba
View commit details
Copy full SHA for b89caba
Browse repository at this point
[None][fix] harden DSA KV cache manager V2 as default
Show description for aa9d946
yizhang-nv
committed
aa9d946
View commit details
Copy full SHA for aa9d946
Browse repository at this point
[None][fix] address DSA KV cache review feedback
Show description for a673749
yizhang-nv
committed
a673749
View commit details
Copy full SHA for a673749
Browse repository at this point
[None][docs] defer KV cache documentation update
Show description for 72b73d6
yizhang-nv
committed
72b73d6
View commit details
Copy full SHA for 72b73d6
Browse repository at this point
[TensorRT-LLM] Fix KV cache V2 CI regressions
Show description for 40cdbb2
yizhang-nv
committed
40cdbb2
View commit details
Copy full SHA for 40cdbb2
Browse repository at this point
[TensorRT-LLM] Fix DSA MTP draft cache replay
Show description for 679b10e
yizhang-nv
committed
679b10e
View commit details
Copy full SHA for 679b10e
Browse repository at this point
refactor: identify native DSA cache managers
Show description for b309e17
yizhang-nv
committed
b309e17
View commit details
Copy full SHA for b309e17
Browse repository at this point
[None][refactor] resolve KV cache defaults via preferences
Show description for 3353119
yizhang-nv
committed
3353119
View commit details
Copy full SHA for 3353119
Browse repository at this point
[None][refactor] finish KV cache preference migration
Show description for f3146d7
yizhang-nv
committed
f3146d7
View commit details
Copy full SHA for f3146d7
Browse repository at this point
You can’t perform that action at this time.