Dockerfile.sglang 22 KB
Newer Older
1
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
# SPDX-License-Identifier: Apache-2.0
3
#
4
5
6
7
8
9
10
11
12
13
14
15
# NOTE FOR dynamo_base AND wheel_builder STAGES:
#
# All changes to dynamo_base and wheel_builder stages should be replicated across
# Dockerfile and Dockerfile.<framework> images.:
#   - Dockerfile
#   - Dockerfile.vllm
#   - Dockerfile.sglang
#   - Dockerfile.trtllm
# This duplication was introduced purposely to quickly enable Docker layer caching and
# deduplication. Please ensure these stages stay in sync until the duplication can be
# addressed.
#
16
17
18
19
20
# Throughout this file, we make certain paths group-writable because this allows
# both the dynamo user (UID 1000) and Dev Container users (UID != 1000) to work
# properly without needing slow chown -R operations (which can add 2-10 extra
# minutes).
#
21
# DEVELOPMENT PATHS THAT MUST BE GROUP-WRITABLE (for virtualenv containers):
22
23
24
25
26
27
28
29
#   /workspace            - Users create/modify project files
#   /home/dynamo          - Users create config/cache files
#   /home/dynamo/.local   - SGLang uses $HOME/.local/lib/python3.10/site-packages for pip install
#
# HOW TO ACHIEVE GROUP-WRITABLE PERMISSIONS:
# 1. SHELL + /etc/profile.d - Login shell sources umask 002 globally for all RUN commands (775/664)
# 2. COPY --chmod=775       - Sets permissions on copied children (not destination)
# 3. chmod g+w (no -R)      - Fixes destination dirs only (milliseconds vs minutes)
30

31
32
33
34
35
36
# This section contains build arguments that are common and shared with
# the plain Dockerfile, so they should NOT have a default. The source of truth is from build.sh.
ARG BASE_IMAGE
ARG BASE_IMAGE_TAG

ARG PYTHON_VERSION
37
38
ARG ENABLE_KVBM
ARG ENABLE_MEDIA_NIXL
39
ARG ENABLE_MEDIA_FFMPEG
40
ARG CARGO_BUILD_JOBS
41

42
43
ARG RUNTIME_IMAGE="lmsysorg/sglang"
ARG RUNTIME_IMAGE_TAG="v0.5.6.post2-runtime"
44

45
# SCCACHE configuration
46
47
48
ARG USE_SCCACHE
ARG SCCACHE_BUCKET=""
ARG SCCACHE_REGION=""
49

50
51
52
53
# NIXL configuration
ARG NIXL_UCX_REF
ARG NIXL_REF
ARG NIXL_GDRCOPY_REF
Joe Chandler's avatar
Joe Chandler committed
54
ARG NIXL_LIBFABRIC_REF
55

56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
# Define general architecture ARGs for supporting both x86 and aarch64 builds.
#   ARCH: Used for package suffixes (e.g., amd64, arm64)
#   ARCH_ALT: Used for Rust targets, manylinux suffix (e.g., x86_64, aarch64)
#
# Default values are for x86/amd64:
#   --build-arg ARCH=amd64 --build-arg ARCH_ALT=x86_64
#
# For arm64/aarch64, build with:
#   --build-arg ARCH=arm64 --build-arg ARCH_ALT=aarch64
#
# NOTE: There isn't an easy way to define one of these values based on the other value
# without adding if statements everywhere, so just define both as ARGs for now.
ARG ARCH=amd64
ARG ARCH_ALT=x86_64

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
167
168
169
170
171
##################################
########## Base Image ############
##################################

FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG} AS dynamo_base

ARG ARCH
ARG ARCH_ALT

USER root
WORKDIR /opt/dynamo

# Install uv package manager
COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/

# Install NATS server
ENV NATS_VERSION="v2.10.28"
RUN --mount=type=cache,target=/var/cache/apt \
    wget --tries=3 --waitretry=5 https://github.com/nats-io/nats-server/releases/download/${NATS_VERSION}/nats-server-${NATS_VERSION}-${ARCH}.deb && \
    dpkg -i nats-server-${NATS_VERSION}-${ARCH}.deb && rm nats-server-${NATS_VERSION}-${ARCH}.deb

# Install etcd
ENV ETCD_VERSION="v3.5.21"
RUN wget --tries=3 --waitretry=5 https://github.com/etcd-io/etcd/releases/download/$ETCD_VERSION/etcd-$ETCD_VERSION-linux-${ARCH}.tar.gz -O /tmp/etcd.tar.gz && \
    mkdir -p /usr/local/bin/etcd && \
    tar -xvf /tmp/etcd.tar.gz -C /usr/local/bin/etcd --strip-components=1 && \
    rm /tmp/etcd.tar.gz
ENV PATH=/usr/local/bin/etcd/:$PATH

# Rust Setup
# Rust environment setup
ENV RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    PATH=/usr/local/cargo/bin:$PATH \
    RUST_VERSION=1.90.0

# Define Rust target based on ARCH_ALT ARG
ARG RUSTARCH=${ARCH_ALT}-unknown-linux-gnu

# Install Rust
RUN wget --tries=3 --waitretry=5 "https://static.rust-lang.org/rustup/archive/1.28.1/${RUSTARCH}/rustup-init" && \
    chmod +x rustup-init && \
    ./rustup-init -y --no-modify-path --profile minimal --default-toolchain $RUST_VERSION --default-host ${RUSTARCH} && \
    rm rustup-init && \
    chmod -R a+w $RUSTUP_HOME $CARGO_HOME


##################################
##### Wheel Build Image ##########
##################################

# Redeclare ARCH_ALT ARG so it's available for interpolation in the FROM instruction
ARG ARCH_ALT

FROM quay.io/pypa/manylinux_2_28_${ARCH_ALT} AS wheel_builder

# Redeclare ARGs for this stage
ARG ARCH
ARG ARCH_ALT
ARG CARGO_BUILD_JOBS

WORKDIR /workspace

# Copy CUDA from base stage
COPY --from=dynamo_base /usr/local/cuda /usr/local/cuda
COPY --from=dynamo_base /etc/ld.so.conf.d/hpcx.conf /etc/ld.so.conf.d/hpcx.conf

# Set environment variables first so they can be used in COPY commands
ENV CARGO_BUILD_JOBS=${CARGO_BUILD_JOBS:-16} \
    RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    CARGO_TARGET_DIR=/opt/dynamo/target \
    PATH=/usr/local/cargo/bin:$PATH

# Copy artifacts from base stage
COPY --from=dynamo_base $RUSTUP_HOME $RUSTUP_HOME
COPY --from=dynamo_base $CARGO_HOME $CARGO_HOME
# Install system dependencies
RUN yum groupinstall -y 'Development Tools' &&  \
    dnf install -y almalinux-release-synergy && \
    dnf config-manager --set-enabled powertools && \
    dnf install -y \
        # Build tools
        cmake \
        ninja-build \
        clang-devel \
        gcc-c++ \
        flex \
        wget \
        # Kernel module build dependencies
        dkms \
        # Protobuf support
        protobuf-compiler \
        # RDMA/InfiniBand support (required for UCX build with --with-verbs)
        libibverbs \
        libibverbs-devel \
        rdma-core \
        rdma-core-devel \
        libibumad \
        libibumad-devel \
        librdmacm-devel \
Joe Chandler's avatar
Joe Chandler committed
172
173
174
175
        numactl-devel \
        # Libfabric support
        hwloc \
        hwloc-devel
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
# Ensure a modern protoc is available (required for --experimental_allow_proto3_optional)
RUN set -eux; \
    PROTOC_VERSION=25.3; \
    case "${ARCH_ALT}" in \
      x86_64) PROTOC_ZIP="protoc-${PROTOC_VERSION}-linux-x86_64.zip" ;; \
      aarch64) PROTOC_ZIP="protoc-${PROTOC_VERSION}-linux-aarch_64.zip" ;; \
      *) echo "Unsupported architecture: ${ARCH_ALT}" >&2; exit 1 ;; \
    esac; \
    wget --tries=3 --waitretry=5 -O /tmp/protoc.zip "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/${PROTOC_ZIP}"; \
    rm -f /usr/local/bin/protoc /usr/bin/protoc; \
    unzip -o /tmp/protoc.zip -d /usr/local bin/protoc include/*; \
    chmod +x /usr/local/bin/protoc; \
    ln -s /usr/local/bin/protoc /usr/bin/protoc; \
    protoc --version

# Point build tools explicitly at the modern protoc
ENV PROTOC=/usr/local/bin/protoc

ENV CUDA_PATH=/usr/local/cuda \
    PATH=/usr/local/cuda/bin:$PATH \
    LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/lib:/usr/local/lib64:$LD_LIBRARY_PATH \
    NVIDIA_DRIVER_CAPABILITIES=video,compute,utility

# Create virtual environment for building wheels
ARG PYTHON_VERSION
ENV VIRTUAL_ENV=/workspace/.venv
RUN uv venv ${VIRTUAL_ENV} --python $PYTHON_VERSION && \
    uv pip install --upgrade meson pybind11 patchelf maturin[patchelf]

ARG NIXL_UCX_REF
ARG NIXL_REF
ARG NIXL_GDRCOPY_REF

# Build and install gdrcopy
RUN git clone --depth 1 --branch ${NIXL_GDRCOPY_REF} https://github.com/NVIDIA/gdrcopy.git && \
    cd gdrcopy/packages && \
    CUDA=/usr/local/cuda ./build-rpm-packages.sh && \
    rpm -Uvh gdrcopy-kmod-*.el8.noarch.rpm && \
    rpm -Uvh gdrcopy-*.el8.${ARCH_ALT}.rpm && \
    rpm -Uvh gdrcopy-devel-*.el8.noarch.rpm

# Install SCCACHE if requested
ARG USE_SCCACHE
ARG SCCACHE_BUCKET
ARG SCCACHE_REGION
COPY container/use-sccache.sh /tmp/use-sccache.sh
RUN if [ "$USE_SCCACHE" = "true" ]; then \
        /tmp/use-sccache.sh install; \
    fi

# Set SCCACHE environment variables
ENV SCCACHE_BUCKET=${USE_SCCACHE:+${SCCACHE_BUCKET}} \
230
    SCCACHE_REGION=${USE_SCCACHE:+${SCCACHE_REGION}}
231

232
# Build FFmpeg from source
milesial's avatar
milesial committed
233
# Do not delete the source tarball for legal reasons
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
ARG FFMPEG_VERSION=7.1
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
if [ "$ENABLE_MEDIA_FFMPEG" = "true" ]; then \
    export SCCACHE_S3_KEY_PREFIX=${SCCACHE_S3_KEY_PREFIX:-${ARCH}} && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export RUSTC_WRAPPER="sccache"; \
    fi && \
    dnf install -y pkg-config && \
    cd /tmp && \
    curl -LO https://ffmpeg.org/releases/ffmpeg-${FFMPEG_VERSION}.tar.xz && \
    tar xf ffmpeg-${FFMPEG_VERSION}.tar.xz && \
    cd ffmpeg-${FFMPEG_VERSION} && \
    ./configure \
        --prefix=/usr/local \
milesial's avatar
milesial committed
251
252
        --disable-gpl \
        --disable-nonfree \
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
        --disable-programs \
        --disable-doc \
        --disable-static \
        --disable-x86asm \
        --disable-postproc \
        --disable-network \
        --disable-encoders \
        --disable-muxers \
        --disable-bsfs \
        --disable-devices \
        --disable-libdrm \
        --enable-shared && \
    make -j$(nproc) && \
    make install && \
    /tmp/use-sccache.sh show-stats "FFMPEG" && \
    ldconfig && \
milesial's avatar
milesial committed
269
270
    mkdir -p /usr/local/src/ffmpeg && \
    mv /tmp/ffmpeg-${FFMPEG_VERSION}* /usr/local/src/ffmpeg/; \
271
272
fi

273
274
275
276
# Build and install UCX
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
277
278
279
280
281
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
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
    cd /usr/local/src && \
     git clone https://github.com/openucx/ucx.git && \
     cd ucx && 			     \
     git checkout $NIXL_UCX_REF &&	 \
     ./autogen.sh &&      \
     ./contrib/configure-release    \
        --prefix=/usr/local/ucx     \
        --enable-shared             \
        --disable-static            \
        --disable-doxygen-doc       \
        --enable-optimizations      \
        --enable-cma                \
        --enable-devel-headers      \
        --with-cuda=/usr/local/cuda \
        --with-verbs                \
        --with-dm                   \
        --with-gdrcopy=/usr/local   \
        --with-efa                  \
        --enable-mt &&              \
     make -j &&                      \
     make -j install-strip &&        \
     /tmp/use-sccache.sh show-stats "UCX" && \
     echo "/usr/local/ucx/lib" > /etc/ld.so.conf.d/ucx.conf && \
     echo "/usr/local/ucx/lib/ucx" >> /etc/ld.so.conf.d/ucx.conf && \
     ldconfig

Joe Chandler's avatar
Joe Chandler committed
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
ARG NIXL_LIBFABRIC_REF
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
    cd /usr/local/src && \
    git clone https://github.com/ofiwg/libfabric.git && \
    cd libfabric && \
    git checkout $NIXL_LIBFABRIC_REF && \
    ./autogen.sh && \
    ./configure --prefix="/usr/local/libfabric" \
                --disable-verbs \
                --disable-psm3 \
                --disable-opx \
                --disable-usnic \
                --disable-rstream \
                --enable-efa \
                --with-cuda=/usr/local/cuda \
                --enable-cuda-dlopen \
                --with-gdrcopy \
                --enable-gdrcopy-dlopen && \
    make -j$(nproc) && \
    make install && \
    /tmp/use-sccache.sh show-stats "LIBFABRIC" && \
    echo "/usr/local/libfabric/lib" > /etc/ld.so.conf.d/libfabric.conf && \
    ldconfig

339
340
341
342
# build and install nixl
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
343
344
345
346
347
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
348
349
350
351
352
353
354
    source ${VIRTUAL_ENV}/bin/activate && \
    git clone --depth 1 --branch ${NIXL_REF} "https://github.com/ai-dynamo/nixl.git" && \
    cd nixl && \
    mkdir build && \
    meson setup build/ --prefix=/opt/nvidia/nvda_nixl --buildtype=release \
    -Dcudapath_lib="/usr/local/cuda/lib64" \
    -Dcudapath_inc="/usr/local/cuda/include" \
Joe Chandler's avatar
Joe Chandler committed
355
356
    -Ducx_path="/usr/local/ucx" \
    -Dlibfabric_path="/usr/local/libfabric" && \
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
    cd build && \
    ninja && \
    ninja install && \
    /tmp/use-sccache.sh show-stats "NIXL"

ENV NIXL_LIB_DIR=/opt/nvidia/nvda_nixl/lib64  \
    NIXL_PLUGIN_DIR=/opt/nvidia/nvda_nixl/lib64/plugins \
    NIXL_PREFIX=/opt/nvidia/nvda_nixl
ENV LD_LIBRARY_PATH=${NIXL_LIB_DIR}:${NIXL_PLUGIN_DIR}:/usr/local/ucx/lib:/usr/local/ucx/lib/ucx:${LD_LIBRARY_PATH}

RUN echo "$NIXL_LIB_DIR" > /etc/ld.so.conf.d/nixl.conf && \
    echo "$NIXL_PLUGIN_DIR" >> /etc/ld.so.conf.d/nixl.conf && \
    ldconfig

RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
374
375
376
377
378
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
379
380
381
382
383
384
385
386
387
388
389
390
391
392
    cd /workspace/nixl && \
    uv build . --out-dir /opt/dynamo/dist/nixl --python $PYTHON_VERSION

# Copy source code (order matters for layer caching)
COPY pyproject.toml README.md LICENSE Cargo.toml Cargo.lock rust-toolchain.toml hatch_build.py /opt/dynamo/
COPY launch/ /opt/dynamo/launch/
COPY lib/ /opt/dynamo/lib/
COPY components/ /opt/dynamo/components/

# Build dynamo wheels
ARG ENABLE_KVBM
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX=${SCCACHE_S3_KEY_PREFIX:-${ARCH}} && \
393
394
395
396
397
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export RUSTC_WRAPPER="sccache"; \
    fi && \
398
399
400
401
    source ${VIRTUAL_ENV}/bin/activate && \
    cd /opt/dynamo && \
    uv build --wheel --out-dir /opt/dynamo/dist && \
    cd /opt/dynamo/lib/bindings/python && \
402
    FEATURES=""; \
403
    if [ "$ENABLE_MEDIA_NIXL" = "true" ]; then \
404
405
406
407
408
409
410
        FEATURES="$FEATURES dynamo-llm/media-nixl"; \
    fi; \
    if [ "$ENABLE_MEDIA_FFMPEG" = "true" ]; then \
        FEATURES="$FEATURES media-ffmpeg"; \
    fi; \
    if [ -n "$FEATURES" ]; then \
        maturin build --release --features "$FEATURES" --out /opt/dynamo/dist; \
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
    else \
        maturin build --release --out /opt/dynamo/dist; \
    fi && \
    if [ "$ENABLE_KVBM" = "true" ]; then \
        cd /opt/dynamo/lib/bindings/kvbm && \
        maturin build --release --out target/wheels && \
        auditwheel repair \
            --exclude libnixl.so \
            --exclude libnixl_build.so \
            --exclude libnixl_common.so \
            --plat manylinux_2_28_${ARCH_ALT} \
            --wheel-dir /opt/dynamo/dist \
            target/wheels/*.whl; \
    fi && \
    /tmp/use-sccache.sh show-stats "Dynamo"
426

427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
##################################
########## Runtime Image #########
##################################

FROM ${RUNTIME_IMAGE}:${RUNTIME_IMAGE_TAG} AS runtime

# cleanup unnecessary libs
RUN apt remove -y python3-apt &&\
    pip uninstall -y termplotlib

# This ARG is still utilized for SGLANG Version extraction
ARG RUNTIME_IMAGE_TAG
WORKDIR /workspace

# Install NATS and ETCD
COPY --from=dynamo_base /usr/bin/nats-server /usr/bin/nats-server
COPY --from=dynamo_base /usr/local/bin/etcd/ /usr/local/bin/etcd/

ENV PATH=/usr/local/bin/etcd:$PATH
446

447
# Create dynamo user with group 0 for OpenShift compatibility
448
449
450
RUN userdel -r ubuntu > /dev/null 2>&1 || true \
    && useradd -m -s /bin/bash -g 0 dynamo \
    && [ `id -u dynamo` -eq 1000 ] \
451
    && mkdir -p /home/dynamo/.cache /opt/dynamo \
452
    # Non-recursive chown - only the directories themselves, not contents
453
    && chown dynamo:0 /home/dynamo /home/dynamo/.cache /opt/dynamo /workspace \
454
455
456
457
    # No chmod needed: umask 002 handles new files, COPY --chmod handles copied content
    # Set umask globally for all subsequent RUN commands (must be done as root before USER dynamo)
    # NOTE: Setting ENV UMASK=002 does NOT work - umask is a shell builtin, not an environment variable
    && mkdir -p /etc/profile.d && echo 'umask 002' > /etc/profile.d/00-umask.sh
458
459

USER dynamo
460
461
# Copy attribution files
COPY --chmod=664 --chown=dynamo:0 ATTRIBUTION* LICENSE /workspace/
462

463
464
465
466
467
# Copy ffmpeg
RUN --mount=type=bind,from=wheel_builder,source=/usr/local/,target=/tmp/usr/local/ \
    cp -rnL /tmp/usr/local/include/libav* /tmp/usr/local/include/libsw* /usr/local/include/; \
    cp -nL /tmp/usr/local/lib/libav*.so /tmp/usr/local/lib/libsw*.so /usr/local/lib/; \
    cp -nL /tmp/usr/local/lib/pkgconfig/libav*.pc /tmp/usr/local/lib/pkgconfig/libsw*.pc /usr/lib/pkgconfig/; \
milesial's avatar
milesial committed
468
    cp -r /tmp/usr/local/src/ffmpeg /usr/local/src/; \
469
470
    true # in case ffmpeg not enabled

471
# Pattern: COPY --chmod=775 <path>; chmod g+w <path> done later as root because COPY --chmod only affects <path>/*, not <path>
472
COPY --chmod=775 --chown=dynamo:0 benchmarks/ /workspace/benchmarks/
473
COPY --chmod=775 --chown=dynamo:0 --from=wheel_builder /opt/dynamo/dist/*.whl /opt/dynamo/wheelhouse/
474

475
476
477
478
479
480
ENV SGLANG_VERSION="${RUNTIME_IMAGE_TAG%%-*}"
RUN --mount=type=bind,source=.,target=/mnt/local_src \
    pip install --no-cache-dir --break-system-packages \
        /opt/dynamo/wheelhouse/ai_dynamo_runtime*.whl \
        /opt/dynamo/wheelhouse/ai_dynamo*any.whl \
        sglang==${SGLANG_VERSION}
481

482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
# Install common and test dependencies
RUN --mount=type=bind,source=.,target=/mnt/local_src \
    pip install --no-cache-dir --break-system-packages \
        --requirement /mnt/local_src/container/deps/requirements.txt \
        --requirement /mnt/local_src/container/deps/requirements.test.txt \
        sglang==${SGLANG_VERSION} && \
    cd /workspace/benchmarks && \
    pip install --break-system-packages --no-cache . && \
    # pip/uv bypasses umask when creating .egg-info files, but chmod -R is fast here (small directory)
    chmod -R g+w /workspace/benchmarks && \
    # Install NVIDIA packages that are needed for DeepEP to work properly
    # This is done in the upstream runtime image too, but we overrode these packages earlier
    pip install --no-cache-dir --break-system-packages --force-reinstall --no-deps \
        nvidia-nccl-cu12==2.28.3 \
        nvidia-cudnn-cu12==9.16.0.29 \
        nvidia-cutlass-dsl==4.3.0

# Copy tests, deploy and components for CI with correct ownership
500
501
502
503
504
505
# Pattern: COPY --chmod=775 <path>; chmod g+w <path> done later as root because COPY --chmod only affects <path>/*, not <path>
COPY --chmod=775 --chown=dynamo:0 tests /workspace/tests
COPY --chmod=775 --chown=dynamo:0 examples /workspace/examples
COPY --chmod=775 --chown=dynamo:0 deploy /workspace/deploy
COPY --chmod=775 --chown=dynamo:0 components/ /workspace/components/
COPY --chmod=775 --chown=dynamo:0 recipes/ /workspace/recipes/
506

507
508
# Enable forceful shutdown of inflight requests
ENV SGLANG_FORCE_SHUTDOWN=1
509

510
511
512
# Our scripting assumes /workspace is where dynamo is located
# In order to maintain the ability to have sglang and dynamo
# in the same workspace, symlink /workspace to /sgl-workspace/dynamo
513
USER root
514
RUN ln -s /workspace /sgl-workspace/dynamo
515
516

USER dynamo
517
ARG DYNAMO_COMMIT_SHA
518
ENV DYNAMO_COMMIT_SHA=${DYNAMO_COMMIT_SHA}
519

520
ENV PATH=/home/dynamo/.local/bin:$PATH
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536

###########################################################
########## Development (run.sh, runs as root user) ########
###########################################################
#
# PURPOSE: Local development environment for use with run.sh (not Dev Container plug-in)
#
# This stage runs as root and provides:
# - Development tools and utilities for local debugging
# - Support for vscode/cursor development outside the Dev Container plug-in
#
# Use this stage if you need a full-featured development environment with extra tools,
# but do not use it with the Dev Container plug-in.

FROM runtime AS dev

537
538
# Don't want ubuntu to be editable, just change uid and gid.
ARG WORKSPACE_DIR=/workspace
539

540
USER root
541
# Install utilities as root
542
543
RUN apt-get update -y && \
    apt-get install -y --no-install-recommends  \
544
    # Install utilities
545
546
    nvtop \
    wget \
547
548
549
    tmux \
    vim \
    git \
550
    openssh-client \
551
    iproute2 \
552
553
    rsync \
    zip \
554
555
556
    unzip \
    htop \
    # Build Dependencies
557
558
559
560
561
    autoconf \
    automake \
    cmake \
    libtool \
    meson \
562
563
564
    net-tools \
    pybind11-dev \
    # Rust build dependencies
565
566
    clang \
    libclang-dev \
567
568
    protobuf-compiler \
    pkg-config && \
569
570
    rm -rf /var/lib/apt/lists/*

571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
# Set umask for group-writable files in dev stage (runs as root)
RUN mkdir -p /etc/profile.d && echo 'umask 002' > /etc/profile.d/00-umask.sh
SHELL ["/bin/bash", "-l", "-o", "pipefail", "-c"]

# Set workspace directory variable
ENV WORKSPACE_DIR=${WORKSPACE_DIR} \
    DYNAMO_HOME=${WORKSPACE_DIR} \
    RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    CARGO_TARGET_DIR=/workspace/target \
    PATH=/usr/local/cargo/bin:$PATH

# Copy rust installation from dynamo_base to avoid duplication efforts
# Pattern: COPY --chmod=775 <path>; chmod g+w <path> because COPY --chmod only affects <path>/*, not <path>
COPY --from=dynamo_base --chmod=775 /usr/local/rustup /usr/local/rustup
COPY --from=dynamo_base --chmod=775 /usr/local/cargo /usr/local/cargo
RUN chmod g+w /usr/local/rustup /usr/local/cargo
588

589
# Install maturin, for maturin develop
590
# Editable install of dynamo
591
592
593
COPY pyproject.toml README.md hatch_build.py /workspace/
RUN pip install maturin[patchelf] && \
    pip install --no-deps -e .
594
595

ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
596
CMD []