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 }}
TheTom
/
llama-cpp-turboquant
Public
forked from
ggml-org/llama.cpp
Uh oh!
There was an error while loading.
Please reload this page
.
Notifications
You must be signed in to change notification settings
Fork
415
Star
2.4k
Code
Issues
25
Pull requests
10
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
vulkan : add rotated mul_mm_id for the TurboQuant weight types
- #266
#266
Merged
TheTom
merged 8 commits into
TheTom:feature/turboquant-kv-cache
TheTom/llama-cpp-turboquant:feature/turboquant-kv-cache
from
Defilan:vulkan/tq-rotated-mm-id
Defilan/llama.cpp:vulkan/tq-rotated-mm-id
Copy head branch name to clipboard
Aug 7, 2026
Conversation
Commits
8
(8)
Checks
Files changed
Merged
vulkan : add rotated mul_mm_id for the TurboQuant weight types
#266
TheTom
merged 8 commits into
TheTom:feature/turboquant-kv-cache
TheTom/llama-cpp-turboquant:feature/turboquant-kv-cache
from
Defilan:vulkan/tq-rotated-mm-id
Defilan/llama.cpp:vulkan/tq-rotated-mm-id
Copy head branch name to clipboard
Commits
Commits on Aug 4, 2026
vulkan : TQ rotated-matmul shader groundwork (A-side loads + activation rotate)
Show description for ffa7b9c
Defilan
committed
ffa7b9c
View commit details
Copy full SHA for ffa7b9c
Browse repository at this point
vulkan : generate TQ rotated matmul and activation-rotate shaders
Show description for 7db79bc
Defilan
committed
7db79bc
View commit details
Copy full SHA for 7db79bc
Browse repository at this point
vulkan : create the TQ activation-rotate pipeline
Show description for b3b493f
Defilan
committed
b3b493f
View commit details
Copy full SHA for b3b493f
Browse repository at this point
vulkan : add FLOAT_TYPEV8 to the TQ matmul float_type_dict
Show description for c9fb885
Defilan
committed
c9fb885
View commit details
Copy full SHA for c9fb885
Browse repository at this point
vulkan : rotate the staged activation copy in place, drop the second buffer
Show description for d4d3543
Defilan
committed
d4d3543
View commit details
Copy full SHA for d4d3543
Browse repository at this point
vulkan : register the TQ rotated mul_mm_id pipelines
Show description for 0239304
Defilan
committed
0239304
View commit details
Copy full SHA for 0239304
Browse repository at this point
vulkan : dispatch the TQ rotated mul_mm_id path
Show description for 94db2e4
Defilan
committed
94db2e4
View commit details
Copy full SHA for 94db2e4
Browse repository at this point
vulkan : apply the TQ MUL_MAT_ID size gate only to the f16 dequant fallback
Show description for 1606490
Defilan
committed
1606490
View commit details
Copy full SHA for 1606490
Browse repository at this point
You can’t perform that action at this time.