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
Accelerator
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 }}
Nathanw1014
/
llama.cpp
Public
forked from
ggml-org/llama.cpp
Notifications
You must be signed in to change notification settings
Fork
5
Star
22
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Prefill improvements: 119 -> 210 tok/s at 32k depth, sparse FA 8.16 -> 1.10 seconds
- #2
#2
Merged
Nathanw1014
merged 5 commits into
Nathanw1014:strix-halo-vulkan
Nathanw1014/llama.cpp:strix-halo-vulkan
from
Mushoz:strix-halo-vulkan
Mushoz/llama.cpp:strix-halo-vulkan
Copy head branch name to clipboard
Aug 17, 2026
Conversation
Commits
5
(5)
Checks
Files changed
Merged
Prefill improvements: 119 -> 210 tok/s at 32k depth, sparse FA 8.16 -> 1.10 seconds
#2
Nathanw1014
merged 5 commits into
Nathanw1014:strix-halo-vulkan
Nathanw1014/llama.cpp:strix-halo-vulkan
from
Mushoz:strix-halo-vulkan
Mushoz/llama.cpp:strix-halo-vulkan
Copy head branch name to clipboard
Commits
Commits on Aug 12, 2026
vulkan: accelerate DeepSeek V4 sparse prefill FA
Show description for 24c7ead
Mushoz
committed
24c7ead
View commit details
Copy full SHA for 24c7ead
Browse repository at this point
Commits on Aug 13, 2026
vulkan: split sparse prefill attention
Show description for 4bbe53e
Mushoz
committed
4bbe53e
View commit details
Copy full SHA for 4bbe53e
Browse repository at this point
vulkan: tile sparse prefill scratch
Show description for 80728f3
Mushoz
committed
80728f3
View commit details
Copy full SHA for 80728f3
Browse repository at this point
vulkan: reuse sparse FA probability fragments
Show description for 733fbbb
Mushoz
committed
733fbbb
View commit details
Copy full SHA for 733fbbb
Browse repository at this point
vulkan: cache sparse FA masks per key block
Show description for 11714b1
Mushoz
committed
11714b1
View commit details
Copy full SHA for 11714b1
Browse repository at this point
You can’t perform that action at this time.