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
Events
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 }}
novkien
llama.cpp-fork
Repository navigation
Code
Issues
2
(2)
Pull requests
Actions
Projects
Security and quality
Insights
More
items
cuda: implement selective CUDA P2P transport
- #4
#4
Merged
novkien
merged 11 commits into
master
novkien/llama.cpp-fork:master
from
docs/issue-3-pair-p2p-preflight-20260930
novkien/llama.cpp-fork:docs/issue-3-pair-p2p-preflight-20260930
Copy head branch name to clipboard
Sep 30, 2026
Conversation
Commits
11
(11)
Checks
Files changed
Merged
cuda: implement selective CUDA P2P transport
#4
novkien
merged 11 commits into
master
novkien/llama.cpp-fork:master
from
docs/issue-3-pair-p2p-preflight-20260930
novkien/llama.cpp-fork:docs/issue-3-pair-p2p-preflight-20260930
Copy head branch name to clipboard
Commits
Commits on Sep 29, 2026
docs : prepare KV cache retention design and junior implementation guide
Show description for 18a6e1e
novkien
committed
18a6e1e
View commit details
Copy full SHA for 18a6e1e
Browse repository at this point
server: preserve slot branch before LCP reuse and rank RAM cache by lcp
Show description for 8cfa7bb
novkien
committed
8cfa7bb
View commit details
Copy full SHA for 8cfa7bb
Browse repository at this point
ci: export the exact cache review source for isolated validation
Show description for c2b7e95
novkien
committed
c2b7e95
View commit details
Copy full SHA for c2b7e95
Browse repository at this point
ci: collect the public tiny model for offline cache regressions
Show description for 6b598d2
novkien
committed
6b598d2
View commit details
Copy full SHA for 6b598d2
Browse repository at this point
ci: complete offline Python 3.13 review dependencies
Show description for fa04884
novkien
committed
fa04884
View commit details
Copy full SHA for fa04884
Browse repository at this point
ci: validate and publish the hash-checked cache review repair
Show description for 09a8b3b
novkien
committed
09a8b3b
View commit details
Copy full SHA for 09a8b3b
Browse repository at this point
server: harden RAM cache retention across slot reuse
Show description for e8ef91d
github-actions[bot]
committed
e8ef91d
View commit details
Copy full SHA for e8ef91d
Browse repository at this point
ci: remove the temporary cache review transport
Show description for 705ee67
novkien
committed
705ee67
View commit details
Copy full SHA for 705ee67
Browse repository at this point
Merge PR#2: server preserve RAM prompt cache across slot reuse
novkien
committed
2138591
View commit details
Copy full SHA for 2138591
Browse repository at this point
Commits on Sep 30, 2026
docs: prepare selective CUDA P2P implementation
Show description for 990a757
novkien
committed
990a757
View commit details
Copy full SHA for 990a757
Browse repository at this point
cuda: implement selective CUDA P2P transport
Show description for ed1d2b9
novkien
committed
ed1d2b9
View commit details
Copy full SHA for ed1d2b9
Browse repository at this point
You can’t perform that action at this time.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=32){kind=avatar}