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

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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