[CPU] Refactor CPU attention backend (#27954)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
@@ -17,6 +17,7 @@
|
||||
# VLLM_CPU_DISABLE_AVX512=false (default)|true
|
||||
# VLLM_CPU_AVX512BF16=false (default)|true
|
||||
# VLLM_CPU_AVX512VNNI=false (default)|true
|
||||
# VLLM_CPU_AMXBF16=false (default)|true
|
||||
#
|
||||
|
||||
######################### COMMON BASE IMAGE #########################
|
||||
@@ -92,6 +93,9 @@ ENV VLLM_CPU_AVX512BF16=${VLLM_CPU_AVX512BF16}
|
||||
# Support for building with AVX512VNNI ISA: docker build --build-arg VLLM_CPU_AVX512VNNI="true" ...
|
||||
ARG VLLM_CPU_AVX512VNNI=0
|
||||
ENV VLLM_CPU_AVX512VNNI=${VLLM_CPU_AVX512VNNI}
|
||||
# Support for building with AMXBF16 ISA: docker build --build-arg VLLM_CPU_AMXBF16="true" ...
|
||||
ARG VLLM_CPU_AMXBF16=0
|
||||
ENV VLLM_CPU_AMXBF16=${VLLM_CPU_AMXBF16}
|
||||
|
||||
WORKDIR /workspace/vllm
|
||||
|
||||
|
||||
Reference in New Issue
Block a user