vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

CUDA: MMQ code deduplication + iquant support (#8495)

Browse source 
* CUDA: MMQ code deduplication + iquant support

* 1 less parallel job for CI build
This commit is contained in:
Johannes Gäßler 2024-07-20 22:25:26 +02:00 • committed by GitHub
parent 07283b1a90
commit 69c487f4ed
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 800 additions and 639 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.github/workflows/build.yml vendored
View file

@ -860,7 +860,7 @@ jobs:
mkdir build
cd build
cmake .. -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=ON
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
cmake --build . --config Release -j $((${env:NUMBER_OF_PROCESSORS} - 1))
- name: Determine tag name
id: tag