ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-19 12:47:52 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity
5582039d0a
whisper.cpp/ggml-cuda/template-instances
History
Johannes Gäßler 5582039d0a CUDA: quantized KV support for FA vec (llama/7527) 
* CUDA: quantized KV support for FA vec

* try CI fix

* fix commented-out kernel variants

* add q8_0 q4_0 tests

* fix nwarps > batch size

* split fattn compile via extern templates

* fix flake8

* fix metal tests

* fix cmake

* make generate_cu_files.py executable

* add autogenerated .cu files

* fix AMD

* error if type_v != FP16 and not flash_attn

* remove obsolete code
2024-06-16 18:19:48 +03:00
..
fattn-vec-f16-instance-hs64-f16-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs64-f16-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs64-f16-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs64-f16-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs64-f16-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs64-f16-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-f16-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-f16-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-f16-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-f16-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-f16-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-f16-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_0-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_0-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_0-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_0-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_0-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_0-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_1-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_1-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_1-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_1-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_1-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q4_1-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_0-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_0-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_0-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_0-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_0-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_0-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_1-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_1-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_1-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_1-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_1-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q5_1-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q8_0-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q8_0-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q8_0-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q8_0-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q8_0-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs128-q8_0-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f16-instance-hs256-f16-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs64-f16-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs64-f16-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs64-f16-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs64-f16-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs64-f16-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs64-f16-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-f16-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-f16-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-f16-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-f16-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-f16-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-f16-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_0-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_0-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_0-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_0-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_0-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_0-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_1-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_1-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_1-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_1-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_1-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q4_1-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_0-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_0-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_0-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_0-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_0-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_0-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_1-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_1-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_1-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_1-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_1-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q5_1-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q8_0-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q8_0-q4_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q8_0-q4_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q8_0-q5_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q8_0-q5_1.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs128-q8_0-q8_0.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-vec-f32-instance-hs256-f16-f16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-wmma-f16-instance-kqfloat-cpb16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-wmma-f16-instance-kqfloat-cpb32.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-wmma-f16-instance-kqhalf-cpb8.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-wmma-f16-instance-kqhalf-cpb16.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
fattn-wmma-f16-instance-kqhalf-cpb32.cu CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00
generate_cu_files.py CUDA: quantized KV support for FA vec (llama/7527) 2024-06-16 18:19:48 +03:00