Splitting attention kernel file (#10091)

Signed-off-by: maleksan85 <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
This commit is contained in:
Aleksandr Malyshev
2024-11-11 22:55:07 -08:00
committed by GitHub
co-authored by Aleksandr Malyshev
parent 7f5edb5900
commit 812c981fa0
4 changed files with 399 additions and 328 deletions
+3 -2
View File
@@ -37,7 +37,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")
set(CUDA_SUPPORTED_ARCHS "7.0;7.5;8.0;8.6;8.9;9.0")
# Supported AMD GPU architectures.
set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100")
set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101")
#
# Supported/expected torch versions for CUDA/ROCm.
@@ -187,7 +187,8 @@ message(STATUS "FetchContent base directory: ${FETCHCONTENT_BASE_DIR}")
set(VLLM_EXT_SRC
"csrc/cache_kernels.cu"
"csrc/attention/attention_kernels.cu"
"csrc/attention/paged_attention_v1.cu"
"csrc/attention/paged_attention_v2.cu"
"csrc/pos_encoding_kernels.cu"
"csrc/activation_kernels.cu"
"csrc/layernorm_kernels.cu"