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
Type
/
to 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 }}
Uh oh!
There was an error while loading.
Please reload this page
.
PrismML-Eng
/
llama.cpp
Public
forked from
ggml-org/llama.cpp
Notifications
You must be signed in to change notification settings
Fork
86
Star
452
Code
Issues
17
Pull requests
14
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
Bit-interleaved Q1_0 8x32 repack kernels for x86 AVX2
- #29
#29
Draft
pl752
wants to merge 11 commits into
PrismML-Eng:prism
PrismML-Eng/llama.cpp:prism
from
pl752:perf/q1_0_8x32_repack_AVX2
pl752/llama.cpp:perf/q1_0_8x32_repack_AVX2
Copy head branch name to clipboard
Conversation
Commits
11
(11)
Checks
Files changed
Draft
Bit-interleaved Q1_0 8x32 repack kernels for x86 AVX2
#29
pl752
wants to merge 11 commits into
PrismML-Eng:prism
PrismML-Eng/llama.cpp:prism
from
pl752:perf/q1_0_8x32_repack_AVX2
pl752/llama.cpp:perf/q1_0_8x32_repack_AVX2
Copy head branch name to clipboard
Commits
Commits on Apr 19, 2026
ggml-cpu: Optimized x86 and generic cpu q1_0 dot (follow up) (#21636)
pl752
authored and
khosravipasha
committed
ca01960
View commit details
Copy full SHA for ca01960
Browse repository at this point
Add release-prism workflow
khosravipasha
committed
7e2a218
View commit details
Copy full SHA for 7e2a218
Browse repository at this point
Add Q2_0 quantization: type definition and CPU backend
khosravipasha
committed
9f31ffc
View commit details
Copy full SHA for 9f31ffc
Browse repository at this point
Add Q2_0 Metal backend
khosravipasha
committed
0eed534
View commit details
Copy full SHA for 0eed534
Browse repository at this point
cuda: Q2_0
khosravipasha
committed
e380897
View commit details
Copy full SHA for e380897
Browse repository at this point
release-prism: install spirv-headers for ubuntu-arm64 vulkan build
khosravipasha
committed
d104cf1
View commit details
Copy full SHA for d104cf1
Browse repository at this point
Commits on May 2, 2026
Implemented bit-interleaved Q1_0 8x32 repack kernels for x86 AVX2
pl752
committed
d11c45d
View commit details
Copy full SHA for d11c45d
Browse repository at this point
Commits on May 5, 2026
Corrected gemv with assumption of nr==1 for consistency
pl752
committed
5a9ab76
View commit details
Copy full SHA for 5a9ab76
Browse repository at this point
Unrolled mm256 registers to avoid register pointers
pl752
committed
3fa569d
View commit details
Copy full SHA for 3fa569d
Browse repository at this point
Split 8 cols to two passes to reduce register pressure
pl752
committed
4e34da1
View commit details
Copy full SHA for 4e34da1
Browse repository at this point
Commits on May 8, 2026
Implement rot4 Q1.0 repack kernels with positive-sum GEMV optimization
pl752
committed
a508eee
View commit details
Copy full SHA for a508eee
Browse repository at this point
You can’t perform that action at this time.