-
Notifications
You must be signed in to change notification settings - Fork 120
/
Dockerfile
29 lines (19 loc) · 1.02 KB
/
Dockerfile
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
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
# FROM vault.habana.ai/gaudi-docker/1.16.1/ubuntu22.04/habanalabs/pytorch-installer-2.2.2:latest as hpu
FROM opea/habanalabs:1.16.1-pytorch-installer-2.2.2 as hpu
ENV LANG=en_US.UTF-8
WORKDIR /home/user/vllm/ray
# copy the source code to the package directory
COPY comps/llms/text-generation/vllm/ray /home/user/vllm/ray
RUN pip install --no-cache-dir --upgrade-strategy eager optimum[habana] && \
pip install --no-cache-dir git+https://github.com/HabanaAI/DeepSpeed.git@1.15.1
RUN pip install --no-cache-dir -v git+https://github.com/HabanaAI/vllm-fork.git@cf6952d
RUN pip install --no-cache-dir "ray>=2.10" "ray[serve,tune]>=2.10"
RUN sed -i 's/#PermitRootLogin prohibit-password/PermitRootLogin yes/' /etc/ssh/sshd_config && \
service ssh restart
ENV PYTHONPATH=$PYTHONPATH:/root:/home/user/vllm/ray
# Required by DeepSpeed
ENV RAY_EXPERIMENTAL_NOSET_HABANA_VISIBLE_MODULES=1
ENV PT_HPU_LAZY_ACC_PAR_MODE=0
ENV PT_HPU_ENABLE_LAZY_COLLECTIVES=true