tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-30 14:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: quantized KV support for FA vec (#7527)

Browse Source 
* 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
This commit is contained in:
Johannes Gäßler
2024-06-01 08:44:14 +02:00
committed by GitHub
parent a323ec60af
commit 9b596417af
110 changed files with 2697 additions and 1200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml-cuda/fattn-tile-f32.cu
View File

@@ -36,6 +36,9 @@ static __global__ void flash_attn_tile_ext_f32(
const int nb11,
const int nb12,
const int nb13,
const int nb21,
const int nb22,
const int nb23,
const int ne0,
const int ne1,
const int ne2,