Skip to content

Navigation Menu

Appearance settings

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

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

ggml-org / llama.cpp Public

Notifications You must be signed in to change notification settings
Fork 12k
Star 81.3k

Code
Issues 333
Pull requests 461
Discussions
Actions
Projects 10
Wiki
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security
Insights

CUDA: quantized KV support for FA vec#7527

Merged

JohannesGaessler merged 14 commits intoggml-org:masterggml-org/llama.cpp:masterfrom

JohannesGaessler:cuda-fattn-vec-quant-3JohannesGaessler/llama.cpp:cuda-fattn-vec-quant-3Copy head branch name to clipboard

Jun 1, 2024

Conversation Commits14 (14)Checks Files changed

Commits

Commits on May 27, 2024

CUDA: quantized KV support for FA vec
JohannesGaessler
committed
try CI fix
JohannesGaessler
committed
fix commented-out kernel variants
JohannesGaessler
committed
add q8_0 q4_0 tests
JohannesGaessler
committed
fix nwarps > batch size
JohannesGaessler
committed

Commits on May 29, 2024

split fattn compile via extern templates
JohannesGaessler
committed
fix flake8
JohannesGaessler
committed
fix metal tests
JohannesGaessler
committed
fix cmake
JohannesGaessler
committed
make generate_cu_files.py executable
JohannesGaessler
committed
add autogenerated .cu files
JohannesGaessler
committed
fix AMD
JohannesGaessler
committed

Commits on May 31, 2024

error if type_v != FP16 and not flash_attn
JohannesGaessler
committed
remove obsolete code
JohannesGaessler
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.