whisper.cpp/ggml
Johannes Gäßler e4bc83ab47 CUDA: refactor and optimize IQ MMVQ (llama/8215)
* CUDA: refactor and optimize IQ MMVQ

* uint -> uint32_t

* __dp4a -> ggml_cuda_dp4a

* remove MIN_CC_DP4A checks

* change default

* try CI fix
2024-07-08 14:53:55 +03:00
..
cmake whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
include whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
src CUDA: refactor and optimize IQ MMVQ (llama/8215) 2024-07-08 14:53:55 +03:00
.gitignore whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
CMakeLists.txt ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (llama/8140) 2024-06-26 23:18:11 +03:00
ggml_vk_generate_shaders.py whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00