forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Dockerfile.rocm
166 lines (138 loc) · 5.35 KB
/
Dockerfile.rocm
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
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
# Default ROCm 6.2 base image
ARG BASE_IMAGE="rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0"
# Default ROCm ARCHes to build vLLM for.
ARG PYTORCH_ROCM_ARCH="gfx908;gfx90a;gfx942;gfx1100"
# Whether to install CK-based flash-attention
# If 0, will not install flash-attention
ARG BUILD_FA="1"
ARG FA_GFX_ARCHS="gfx90a;gfx942"
ARG FA_BRANCH="3cea2fb"
# Whether to build triton on rocm
ARG BUILD_TRITON="1"
ARG TRITON_BRANCH="e192dba"
### Base image build stage
FROM $BASE_IMAGE AS base
# Import arg(s) defined before this build stage
ARG PYTORCH_ROCM_ARCH
# Install some basic utilities
RUN apt-get update && apt-get install python3 python3-pip -y
RUN apt-get update && apt-get install -y \
curl \
ca-certificates \
sudo \
git \
bzip2 \
libx11-6 \
build-essential \
wget \
unzip \
tmux \
ccache \
&& rm -rf /var/lib/apt/lists/*
# When launching the container, mount the code directory to /vllm-workspace
ARG APP_MOUNT=/vllm-workspace
WORKDIR ${APP_MOUNT}
RUN python3 -m pip install --upgrade pip
# Remove sccache so it doesn't interfere with ccache
# TODO: implement sccache support across components
RUN apt-get purge -y sccache; python3 -m pip uninstall -y sccache; rm -f "$(which sccache)"
# Install torch == 2.6.0 on ROCm
RUN --mount=type=cache,target=/root/.cache/pip \
case "$(ls /opt | grep -Po 'rocm-[0-9]\.[0-9]')" in \
*"rocm-6.2"*) \
python3 -m pip uninstall -y torch torchvision \
&& python3 -m pip install --pre \
torch==2.6.0.dev20240918 \
setuptools-scm>=8 \
torchvision==0.20.0.dev20240918 \
--extra-index-url https://download.pytorch.org/whl/nightly/rocm6.2;; \
*) ;; esac
ENV LLVM_SYMBOLIZER_PATH=/opt/rocm/llvm/bin/llvm-symbolizer
ENV PATH=$PATH:/opt/rocm/bin:/libtorch/bin:
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/lib/:/libtorch/lib:
ENV CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/libtorch/include:/libtorch/include/torch/csrc/api/include/:/opt/rocm/include/:
ENV PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH}
ENV CCACHE_DIR=/root/.cache/ccache
### AMD-SMI build stage
FROM base AS build_amdsmi
# Build amdsmi wheel always
RUN cd /opt/rocm/share/amd_smi \
&& python3 -m pip wheel . --wheel-dir=/install
### Flash-Attention wheel build stage
FROM base AS build_fa
ARG BUILD_FA
ARG FA_GFX_ARCHS
ARG FA_BRANCH
# Build ROCm flash-attention wheel if `BUILD_FA = 1`
RUN --mount=type=cache,target=${CCACHE_DIR} \
if [ "$BUILD_FA" = "1" ]; then \
mkdir -p libs \
&& cd libs \
&& git clone https://github.com/ROCm/flash-attention.git \
&& cd flash-attention \
&& git checkout "${FA_BRANCH}" \
&& git submodule update --init \
&& GPU_ARCHS="${FA_GFX_ARCHS}" python3 setup.py bdist_wheel --dist-dir=/install; \
# Create an empty directory otherwise as later build stages expect one
else mkdir -p /install; \
fi
### Triton wheel build stage
FROM base AS build_triton
ARG BUILD_TRITON
ARG TRITON_BRANCH
# Build triton wheel if `BUILD_TRITON = 1`
RUN --mount=type=cache,target=${CCACHE_DIR} \
if [ "$BUILD_TRITON" = "1" ]; then \
mkdir -p libs \
&& cd libs \
&& python3 -m pip install ninja cmake wheel pybind11 \
&& git clone https://github.com/OpenAI/triton.git \
&& cd triton \
&& git checkout "${TRITON_BRANCH}" \
&& cd python \
&& python3 setup.py bdist_wheel --dist-dir=/install; \
# Create an empty directory otherwise as later build stages expect one
else mkdir -p /install; \
fi
### Final vLLM build stage
FROM base AS final
# Import the vLLM development directory from the build context
COPY . .
# Package upgrades for useful functionality or to avoid dependency issues
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install --upgrade numba scipy huggingface-hub[cli] pytest-shard
# Workaround for ray >= 2.10.0
ENV RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
# Silences the HF Tokenizers warning
ENV TOKENIZERS_PARALLELISM=false
RUN --mount=type=cache,target=${CCACHE_DIR} \
--mount=type=bind,source=.git,target=.git \
--mount=type=cache,target=/root/.cache/pip \
python3 -m pip install -Ur requirements-rocm.txt \
&& python3 setup.py clean --all \
&& python3 setup.py develop
# Copy amdsmi wheel into final image
RUN --mount=type=bind,from=build_amdsmi,src=/install,target=/install \
mkdir -p libs \
&& cp /install/*.whl libs \
# Preemptively uninstall to avoid same-version no-installs
&& python3 -m pip uninstall -y amdsmi;
# Copy triton wheel(s) into final image if they were built
RUN --mount=type=bind,from=build_triton,src=/install,target=/install \
mkdir -p libs \
&& if ls /install/*.whl; then \
cp /install/*.whl libs \
# Preemptively uninstall to avoid same-version no-installs
&& python3 -m pip uninstall -y triton; fi
# Copy flash-attn wheel(s) into final image if they were built
RUN --mount=type=bind,from=build_fa,src=/install,target=/install \
mkdir -p libs \
&& if ls /install/*.whl; then \
cp /install/*.whl libs \
# Preemptively uninstall to avoid same-version no-installs
&& python3 -m pip uninstall -y flash-attn; fi
# Install wheels that were built to the final image
RUN --mount=type=cache,target=/root/.cache/pip \
if ls libs/*.whl; then \
python3 -m pip install libs/*.whl; fi
CMD ["/bin/bash"]