CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: use mma PTX instructions for FlashAttention (#11583)

Browse Source 
* CUDA: use mma PTX instructions for FlashAttention

* __shfl_sync workaround for movmatrix

* add __shfl_sync to HIP

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Johannes Gäßler
2025-02-02 19:31:09 +01:00
committed by GitHub
parent 84ec8a58f7
commit 864a0b67a6
29 changed files with 2058 additions and 998 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -596,7 +596,7 @@ ifdef GGML_RPC
OBJ_GGML_EXT += ggml/src/ggml-rpc.o
endif # GGML_RPC
OBJ_CUDA_TMPL = $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-wmma*.cu))
OBJ_CUDA_TMPL = $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-mma*.cu))
OBJ_CUDA_TMPL += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/mmq*.cu))
ifdef GGML_CUDA_FA_ALL_QUANTS