Skip to content

CUDA : faster k-quant dot kernels #1862

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Jun 16, 2023
Merged

CUDA : faster k-quant dot kernels #1862

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
dc67f1a
cuda : faster k-quant dot kernels
Kawrakow Jun 14, 2023
7ced197
Imrove Q2_K dot kernel on older GPUs
Kawrakow Jun 16, 2023
3edee08
Imrove Q6_K dot kernel on older GPUs
Kawrakow Jun 16, 2023
31b2075
Add LLAMA_CUDA_KQUANTS_ITER to CMakeLists.txt and Makefile
Kawrakow Jun 16, 2023
0dc0b69
PR comments
Kawrakow Jun 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,7 @@ set(LLAMA_BLAS_VENDOR "Generic" CACHE STRING "llama: BLAS library vendor")
option(LLAMA_CUBLAS "llama: use cuBLAS" OFF)
set(LLAMA_CUDA_DMMV_X "32" CACHE STRING "llama: x stride for dmmv CUDA kernels")
set(LLAMA_CUDA_DMMV_Y "1" CACHE STRING "llama: y block size for dmmv CUDA kernels")
set(LLAMA_CUDA_KQUANTS_ITER "2" CACHE STRING "llama: iters./thread per block for Q2_K/Q6_K")
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
option(LLAMA_METAL "llama: use Metal" OFF)
option(LLAMA_K_QUANTS "llama: use k-quants" ON)
Expand Down Expand Up @@ -190,6 +191,7 @@ if (LLAMA_CUBLAS)
add_compile_definitions(GGML_USE_CUBLAS)
add_compile_definitions(GGML_CUDA_DMMV_X=${LLAMA_CUDA_DMMV_X})
add_compile_definitions(GGML_CUDA_DMMV_Y=${LLAMA_CUDA_DMMV_Y})
add_compile_definitions(K_QUANTS_PER_ITERATION=${LLAMA_CUDA_KQUANTS_ITER})

if (LLAMA_STATIC)
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
Expand Down
5 changes: 5 additions & 0 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,6 +171,11 @@ ifdef LLAMA_CUDA_DMMV_Y
else
NVCCFLAGS += -DGGML_CUDA_DMMV_Y=1
endif # LLAMA_CUDA_DMMV_Y
ifdef LLAMA_CUDA_KQUANTS_ITER
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=$(LLAMA_CUDA_KQUANTS_ITER)
else
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
endif
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
endif # LLAMA_CUBLAS
Expand Down
Loading