forked from smallcloudai/refact
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile.base
35 lines (31 loc) · 1.05 KB
/
Dockerfile.base
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
ENV INSTALL_OPTIONAL=TRUE
ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
ENV MAX_JOBS=8
RUN apt-get update
RUN DEBIAN_FRONTEND="noninteractive" TZ=Etc/UTC apt-get install -y \
git \
python3 \
python3-pip \
python3-packaging \
expect \
ruby-full \
ruby-bundler \
build-essential \
cmake \
pkg-config \
libicu-dev \
zlib1g-dev \
libcurl4-openssl-dev \
libssl-dev \
&& rm -rf /var/lib/{apt,dpkg,cache,log}
RUN git clone https://github.com/smallcloudai/linguist.git /tmp/linguist \
&& cd /tmp/linguist \
&& bundle install \
&& rake build_gem
ENV PATH="${PATH}:/tmp/linguist/bin"
RUN pip install --no-cache-dir torch==2.1.2 --index-url https://download.pytorch.org/whl/cu118
RUN pip install --no-cache-dir xformers==0.0.23.post1 --index-url https://download.pytorch.org/whl/cu118
RUN pip install ninja
RUN pip install -v git+https://github.com/smallcloudai/flash-attention@feat/alibi
RUN pip install -v git+https://github.com/smallcloudai/vllm@refact_model_deps