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] enable zero-copy token passing in KVCacheManagerV2
- #17308
#17308
Merged
lowsfer
merged 12 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
lowsfer:kvcm2-cpp-follow-up
lowsfer/TensorRT-LLM:kvcm2-cpp-follow-up
Copy head branch name to clipboard
Aug 11, 2026
Conversation
Commits
12
(12)
Checks
Files changed
Merged
[None][perf] enable zero-copy token passing in KVCacheManagerV2
#17308
lowsfer
merged 12 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
lowsfer:kvcm2-cpp-follow-up
lowsfer/TensorRT-LLM:kvcm2-cpp-follow-up
Copy head branch name to clipboard
Commits
Commits on Aug 10, 2026
[None][docs] add KVCacheManagerV2 C++ development guide
Show description for 21c3b10
lowsfer
committed
21c3b10
View commit details
Copy full SHA for 21c3b10
Browse repository at this point
[None][refactor] simplify KVCacheManagerV2 token and key handling
Show description for 8860441
lowsfer
committed
8860441
View commit details
Copy full SHA for 8860441
Browse repository at this point
[None][perf] KVv2: zero-copy int32 token ingest on the block-reuse hot path
Show description for 7e87d33
lowsfer
committed
7e87d33
View commit details
Copy full SHA for 7e87d33
Browse repository at this point
[None][fix] filter partial KV cache event coverage
Show description for ebd6115
lowsfer
committed
ebd6115
View commit details
Copy full SHA for ebd6115
Browse repository at this point
[None][test] cover KV cache event derivation with real blocks
Show description for aece44e
lowsfer
committed
aece44e
View commit details
Copy full SHA for aece44e
Browse repository at this point
[None][fix] order KV cache tree teardown before storage
Show description for c792b3e
lowsfer
committed
c792b3e
View commit details
Copy full SHA for c792b3e
Browse repository at this point
[None][fix] harden KVCacheManagerV2 edge cases
Show description for 66f6b35
lowsfer
committed
66f6b35
View commit details
Copy full SHA for 66f6b35
Browse repository at this point
[None][fix] address KVCacheManagerV2 review follow-ups
Show description for 27693ca
lowsfer
committed
27693ca
View commit details
Copy full SHA for 27693ca
Browse repository at this point
[None][fix] drop stale SsmCommittedPage references in KVCacheManagerV2 introspection
Show description for ab865ac
lowsfer
committed
ab865ac
View commit details
Copy full SHA for ab865ac
Browse repository at this point
[None][fix] add get_tokens_view to KVCacheManagerV2 test request fakes
Show description for 44eb9fa
lowsfer
committed
44eb9fa
View commit details
Copy full SHA for 44eb9fa
Browse repository at this point
[None][fix] address KVCacheManagerV2 review feedback
Show description for 4fbd212
lowsfer
committed
4fbd212
View commit details
Copy full SHA for 4fbd212
Browse repository at this point
[None][perf] inline the TokenIdExt hot path and constrain zero-copy ingest to CPU
Show description for cb56bff
lowsfer
committed
cb56bff
View commit details
Copy full SHA for cb56bff
Browse repository at this point
You can’t perform that action at this time.