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

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
110 changed files with 2697 additions and 1200 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml-cuda.cu
View file

@ -2905,10 +2905,14 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
#if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
return op->src[0]->ne[0] == 64 || op->src[0]->ne[0] == 128;
#else
if (op->src[0]->ne[0] == 64 || op->src[0]->ne[0] == 128) {
if (op->src[0]->ne[0] == 128) {
return true;
}
return ggml_cuda_info().devices[cuda_ctx->device].cc >= CC_VOLTA;
if (op->src[0]->ne[0] == 64 && op->src[1]->type == GGML_TYPE_F16) {
return true;
}
return ggml_cuda_info().devices[cuda_ctx->device].cc >= CC_VOLTA &&
op->src[1]->type == GGML_TYPE_F16 && op->src[2]->type == GGML_TYPE_F16;
#endif // defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
default:
return false;