Dockerfile 10.7 KB
Newer Older
1
2
ARG CUDA_VERSION=12.6.1
FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04
3

Yineng Zhang's avatar
Yineng Zhang committed
4
ARG BUILD_TYPE=all
5
ARG DEEPEP_COMMIT=b6ce310bb0b75079682d09bc2ebc063a074fbd58
6
ARG CMAKE_BUILD_PARALLEL_LEVEL=2
7
8
9
10
ENV DEBIAN_FRONTEND=noninteractive \
    CUDA_HOME=/usr/local/cuda \
    GDRCOPY_HOME=/usr/src/gdrdrv-2.4.4/ \
    NVSHMEM_DIR=/sgl-workspace/nvshmem/install
Ying Sheng's avatar
Ying Sheng committed
11

12
# Set timezone and install all packages
Ying Sheng's avatar
Ying Sheng committed
13
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
14
15
16
17
18
 && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
 && apt-get update && apt-get install -y --no-install-recommends \
    tzdata \
    software-properties-common netcat-openbsd kmod unzip openssh-server \
    curl wget lsof zsh ccache tmux htop git-lfs tree \
19
    python3 python3-pip python3-dev libpython3-dev python3-venv \
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
    build-essential cmake \
    libopenmpi-dev libnuma1 libnuma-dev \
    libibverbs-dev libibverbs1 libibumad3 \
    librdmacm1 libnl-3-200 libnl-route-3-200 libnl-route-3-dev libnl-3-dev \
    ibverbs-providers infiniband-diags perftest \
    libgoogle-glog-dev libgtest-dev libjsoncpp-dev libunwind-dev \
    libboost-all-dev libssl-dev \
    libgrpc-dev libgrpc++-dev libprotobuf-dev protobuf-compiler-grpc \
    pybind11-dev \
    libhiredis-dev libcurl4-openssl-dev \
    libczmq4 libczmq-dev \
    libfabric-dev \
    patchelf \
    nvidia-dkms-550 \
    devscripts debhelper fakeroot dkms check libsubunit0 libsubunit-dev \
 && ln -sf /usr/bin/python3 /usr/bin/python \
 && rm -rf /var/lib/apt/lists/* \
 && apt-get clean

# GDRCopy installation
RUN mkdir -p /tmp/gdrcopy && cd /tmp \
 && git clone https://github.com/NVIDIA/gdrcopy.git -b v2.4.4 \
 && cd gdrcopy/packages \
 && CUDA=/usr/local/cuda ./build-deb-packages.sh \
 && dpkg -i gdrdrv-dkms_*.deb libgdrapi_*.deb gdrcopy-tests_*.deb gdrcopy_*.deb \
 && cd / && rm -rf /tmp/gdrcopy
46

47
48
49
50
# Fix DeepEP IBGDA symlink
RUN ln -sf /usr/lib/x86_64-linux-gnu/libmlx5.so.1 /usr/lib/x86_64-linux-gnu/libmlx5.so

# Clone and install SGLang
Ying Sheng's avatar
Ying Sheng committed
51
WORKDIR /sgl-workspace
52
53
54
55
56
57
58
59
60
61
RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools wheel html5lib six \
 && git clone --depth=1 https://github.com/sgl-project/sglang.git \
 && cd sglang \
 && case "$CUDA_VERSION" in \
      12.6.1) CUINDEX=126 ;; \
      12.8.1) CUINDEX=128 ;; \
      *) echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1 ;; \
    esac \
 && python3 -m pip install --no-cache-dir -e "python[${BUILD_TYPE}]" --extra-index-url https://download.pytorch.org/whl/cu${CUINDEX} \
 && if [ "$CUDA_VERSION" = "12.8.1" ]; then \
62
      python3 -m pip install --no-cache-dir nvidia-nccl-cu12==2.27.6 --force-reinstall --no-deps ; \
63
      python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.2.6/sgl_kernel-0.2.6+cu128-cp39-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \
64
65
66
    fi

# Build and install NVSHMEM + DeepEP
67
RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/source/nvshmem_src_cuda12-all-all-3.3.9.tar.gz \
68
 && git clone https://github.com/deepseek-ai/DeepEP.git \
69
70
 && cd DeepEP && git checkout ${DEEPEP_COMMIT} && cd .. \
 && tar -xf nvshmem_src_cuda12-all-all-3.3.9.tar.gz && mv nvshmem_src nvshmem \
71
 && cd nvshmem \
72
 && rm -f /sgl-workspace/nvshmem_src_cuda12-all-all-3.3.9.tar.gz \
73
74
75
76
77
78
79
80
81
 && NVSHMEM_SHMEM_SUPPORT=0 \
    NVSHMEM_UCX_SUPPORT=0 \
    NVSHMEM_USE_NCCL=0 \
    NVSHMEM_MPI_SUPPORT=0 \
    NVSHMEM_IBGDA_SUPPORT=1 \
    NVSHMEM_PMIX_SUPPORT=0 \
    NVSHMEM_TIMEOUT_DEVICE_POLLING=0 \
    NVSHMEM_USE_GDRCOPY=1 \
    cmake -S . -B build/ -DCMAKE_INSTALL_PREFIX=${NVSHMEM_DIR} -DCMAKE_CUDA_ARCHITECTURES=90 \
82
 && cmake --build build --target install -j${CMAKE_BUILD_PARALLEL_LEVEL} \
83
84
 && cd /sgl-workspace/DeepEP \
 && NVSHMEM_DIR=${NVSHMEM_DIR} pip install .
Ying Sheng's avatar
Ying Sheng committed
85

86
87
88
# Python tools
RUN python3 -m pip install --no-cache-dir \
    datamodel_code_generator \
89
    mooncake_transfer_engine==0.3.4.post2 \
90
91
92
93
94
95
96
97
    pre-commit \
    pytest \
    black \
    isort \
    icdiff \
    uv \
    wheel \
    scikit-build-core
Yineng Zhang's avatar
Yineng Zhang committed
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
# Install development tools and utilities
RUN apt-get update && apt-get install -y \
    gdb \
    ninja-build \
    vim \
    tmux \
    htop \
    wget \
    curl \
    locales \
    lsof \
    git \
    git-lfs \
    zsh \
    tree \
    silversearcher-ag \
    cloc \
    unzip \
    pkg-config \
    libssl-dev \
    bear \
    ccache \
    less \
    && apt install -y rdma-core infiniband-diags openssh-server perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get clean

RUN apt update -y \
    && apt install -y --no-install-recommends gnupg \
    && echo "deb http://developer.download.nvidia.com/devtools/repos/ubuntu2004/amd64 /" | tee /etc/apt/sources.list.d/nvidia-devtools.list \
    && apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub \
    && apt update -y \
    && apt install nsight-systems-cli -y

# Set up locale
RUN locale-gen en_US.UTF-8
ENV LANG en_US.UTF-8
ENV LANGUAGE en_US:en
ENV LC_ALL en_US.UTF-8

# Install minimal Python packages
RUN python3 -m pip install --no-cache-dir --break-system-packages \
    pytest \
    black \
    isort \
    icdiff \
    scikit_build_core \
    uv \
147
148
149
150
    pre-commit \
    pandas \
    matplotlib \
    tabulate
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330

# Install diff-so-fancy
RUN curl -LSso /usr/local/bin/diff-so-fancy https://github.com/so-fancy/diff-so-fancy/releases/download/v1.4.4/diff-so-fancy \
    && chmod +x /usr/local/bin/diff-so-fancy

# Install clang-format
RUN curl -LSso /usr/local/bin/clang-format https://github.com/muttleyxd/clang-tools-static-binaries/releases/download/master-32d3ac78/clang-format-16_linux-amd64 \
    && chmod +x /usr/local/bin/clang-format

# Install clangd
RUN curl -L https://github.com/clangd/clangd/releases/download/18.1.3/clangd-linux-18.1.3.zip -o clangd.zip \
    && unzip clangd.zip \
    && cp -r clangd_18.1.3/bin/* /usr/local/bin/ \
    && cp -r clangd_18.1.3/lib/* /usr/local/lib/ \
    && rm -rf clangd_18.1.3 clangd.zip

# Install CMake
RUN wget https://github.com/Kitware/CMake/releases/download/v3.31.1/cmake-3.31.1-linux-x86_64.tar.gz \
    && tar -xzf cmake-3.31.1-linux-x86_64.tar.gz \
    && cp -r cmake-3.31.1-linux-x86_64/bin/* /usr/local/bin/ \
    && cp -r cmake-3.31.1-linux-x86_64/share/* /usr/local/share/ \
    && rm -rf cmake-3.31.1-linux-x86_64 cmake-3.31.1-linux-x86_64.tar.gz

# Add yank script
COPY --chown=root:root <<-"EOF" /usr/local/bin/yank
#!/bin/bash
put() {
  esc=$1
  test -n "$TMUX" -o -z "${TERM##screen*}" && esc="\033Ptmux;\033$esc\033\\"
  printf "$esc"
}
put "\033]52;c;!\a"
buf=$( cat "$@" )
len=$( printf %s "$buf" | wc -c ) max=74994
test $len -gt $max && echo "$0: input is $(( len - max )) bytes too long" >&2
put "\033]52;c;$( printf %s "$buf" | head -c $max | base64 | tr -d '\r\n' )\a"
test -n "$TMUX" && tmux set-buffer "$buf" ||:
EOF

RUN chmod +x /usr/local/bin/yank

# Install oh-my-zsh and plugins
RUN sh -c "$(curl -fsSL https://raw.githubusercontent.com/ohmyzsh/ohmyzsh/master/tools/install.sh)" "" --unattended \
    && git clone https://github.com/zsh-users/zsh-autosuggestions ${ZSH_CUSTOM:-~/.oh-my-zsh/custom}/plugins/zsh-autosuggestions \
    && git clone https://github.com/zsh-users/zsh-syntax-highlighting.git ${ZSH_CUSTOM:-~/.oh-my-zsh/custom}/plugins/zsh-syntax-highlighting

# Configure Vim
COPY --chown=root:root <<-"EOF" /root/.vimrc
function! Yank(text) abort
  let escape = system('yank', a:text)
  if v:shell_error
    echoerr escape
  else
    call writefile([escape], '/dev/tty', 'b')
  endif
endfunction

noremap <silent> <Leader>y y:<C-U>call Yank(@0)<CR>

" automatically run yank(1) whenever yanking in Vim
function! CopyYank() abort
  call Yank(join(v:event.regcontents, "\n"))
endfunction

autocmd TextYankPost * call CopyYank()

" Basic settings
set number
syntax on
set mouse=a
filetype indent on

" Indentation
set autoindent nosmartindent
set smarttab
set expandtab
set shiftwidth=4
set softtabstop=4

" Visual guides
set colorcolumn=120
highlight ColorColumn ctermbg=5

" Status line
set laststatus=2
set statusline=%<%f\ %h%m%r%=%{\"[\".(&fenc==\"\"?&enc:&fenc).((exists(\"+bomb\")\ &&\ &bomb)?\",B\":\"\").\"]\ \"}%k\ %-14.(%l,%c%V%)\ %P

" Backspace behavior
set backspace=2

" Encoding
set encoding=utf-8
set fileencoding=utf-8
EOF

# Configure tmux
COPY --chown=root:root <<-"EOF" /root/.tmux.conf
# Pane border styling
set -g pane-border-style fg='#742727',bg=black
set -g pane-active-border-style fg=red,bg=black

# Status bar styling
set -g status-style bg='#0C8A92',fg=black

# Change prefix key to backtick
set-option -g prefix `
unbind C-b
bind-key ` send-prefix

# Split panes using - and = with current path
unbind '"'
bind - splitw -v -c '#{pane_current_path}'
unbind '%'
bind = splitw -h -c '#{pane_current_path}'

# Vi mode settings
bind-key -T copy-mode-vi Y send-keys -X copy-pipe 'yank > #{pane_tty}'
set-window-option -g mode-keys vi

# Other settings
set-option -g escape-time 0
set-option -g base-index 1
set-window-option -g mouse on
EOF

# Configure Git
RUN git config --global core.editor "vim" \
    && git config --global core.whitespace "fix,-indent-with-non-tab,trailing-space,cr-at-eol" \
    && git config --global core.pager "diff-so-fancy | less --tabs=4 -RFX" \
    && git config --global color.ui true \
    && git config --global color."diff-highlight".oldNormal "red bold" \
    && git config --global color."diff-highlight".oldHighlight "red bold 52" \
    && git config --global color."diff-highlight".newNormal "green bold" \
    && git config --global color."diff-highlight".newHighlight "green bold 22" \
    && git config --global color.diff.meta "11" \
    && git config --global color.diff.frag "magenta bold" \
    && git config --global color.diff.commit "yellow bold" \
    && git config --global color.diff.old "red bold" \
    && git config --global color.diff.new "green bold" \
    && git config --global color.diff.whitespace "red reverse" \
    && git config --global alias.lg "log --color --graph --pretty=format:'%Cred%h%Creset - %s %Cgreen(%cr) %C(bold blue)<%an>%Creset%C(auto)%d%Creset' --abbrev-commit --" \
    && git config --global http.sslVerify false \
    && git config --global pull.rebase true

# Configure zsh
COPY --chown=root:root <<-"EOF" /root/.zshrc
export ZSH="/root/.oh-my-zsh"

# Theme
ZSH_THEME="robbyrussell"

# Plugins
plugins=(
    git
    z
    zsh-autosuggestions
    zsh-syntax-highlighting
)

source $ZSH/oh-my-zsh.sh

# Aliases
alias ll='ls -alF'
alias la='ls -A'
alias l='ls -CF'
alias vi='vim'

# Enhanced history
HISTSIZE=10000
SAVEHIST=10000
setopt HIST_IGNORE_ALL_DUPS
setopt HIST_FIND_NO_DUPS
setopt INC_APPEND_HISTORY
EOF

RUN set -euxo ; \
    curl --proto '=https' --tlsv1.2 -sSf https://just.systems/install.sh | bash -s -- --to /usr/local/bin

# Set workspace directory
WORKDIR /sgl-workspace/sglang