huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Change the dockerfile. It builds locally, something might be up in AWS

Browse Source 
env.
This commit is contained in:
Nicolas Patry 2024-05-15 13:58:59 +00:00
parent 368c057cbf
commit dc0b8d76b5
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@ -96,6 +96,7 @@ WORKDIR /usr/src
COPY server/Makefile-flash-att Makefile COPY server/Makefile-flash-att Makefile
# Build specific version of flash attention # Build specific version of flash attention
ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
RUN make build-flash-attention RUN make build-flash-attention
# Build Flash Attention v2 CUDA kernels # Build Flash Attention v2 CUDA kernels
@ -107,6 +108,7 @@ 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-cuda RUN make build-flash-attention-v2-cuda
RUN TORCH_CUDA_ARCH_LIST="7.5;8.0;8.6;9.0+PTX" make build-flash-attention
# Build Transformers exllama kernels # Build Transformers exllama kernels
FROM kernel-builder as exllama-kernels-builder FROM kernel-builder as exllama-kernels-builder
@ -181,7 +183,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
ca-certificates \ ca-certificates \
make \ make \
curl \ curl \
build-essential \ git \
&& rm -rf /var/lib/apt/lists/* && rm -rf /var/lib/apt/lists/*
# Copy conda with PyTorch installed # Copy conda with PyTorch installed