ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case (#12183)

Browse source 
- Find out active blocks per SM using cudaOccupancyMaxActiveBlocksPerMultiprocessor API. Use this value to determine the optimal parallel_blocks value.
- Prefer vector flash attention kernels over MMA kernel for BS=1

Fixes Issue: #12182
---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Gaurav Garg 2025-03-20 01:22:06 +05:30 • committed by GitHub
parent a9b59288e2
commit 517b5ddbf0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 214 additions and 266 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml/src/ggml-cuda/ggml-cuda.cu
View file

@ -3230,6 +3230,9 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
#ifndef FLASH_ATTN_AVAILABLE
return false;
#endif // FLASH_ATTN_AVAILABLE
if (op->src[0]->ne[3] != 1) {
return false;
}
if (op->src[1]->type == GGML_TYPE_BF16 || op->src[2]->type == GGML_TYPE_BF16) {
return false;
}