huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix dockerfile

Browse Source
This commit is contained in:
OlivierDehaene 2023-07-18 15:29:02 +02:00
parent d186b13c59
commit 751f26b66c
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
Dockerfile
View File

@ -98,13 +98,6 @@ COPY server/Makefile-flash-att Makefile
# Build specific version of flash attention # Build specific version of flash attention
RUN make build-flash-attention RUN make build-flash-attention
# Build Transformers CUDA kernels
FROM kernel-builder as custom-kernels-builder
WORKDIR /usr/src
COPY server/custom_kernels/ .
# Build Flash Attention v2 CUDA kernels # Build Flash Attention v2 CUDA kernels
FROM kernel-builder as flash-att-v2-builder FROM kernel-builder as flash-att-v2-builder
@ -115,6 +108,13 @@ COPY server/Makefile-flash-att-v2 Makefile
# Build specific version of flash attention v2 # Build specific version of flash attention v2
RUN make build-flash-attention-v2 RUN make build-flash-attention-v2
# Build Transformers CUDA kernels
FROM kernel-builder as custom-kernels-builder
WORKDIR /usr/src
COPY server/custom_kernels/ .
# Build specific version of transformers # Build specific version of transformers
RUN python setup.py build RUN python setup.py build