Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b3f5c97dec | ||
|
|
b3ab0f4349 | ||
|
|
f415438eb9 |
No files matched your search
@@ -108,7 +108,10 @@ steps:
|
|||||||
depends_on: upload-merge-pipeline
|
depends_on: upload-merge-pipeline
|
||||||
steps:
|
steps:
|
||||||
- label: "Entrypoint Test with H100"
|
- label: "Entrypoint Test with H100"
|
||||||
timeout_in_minutes: 60
|
# The suite relaunches an OmniServer per test class (~30 model loads,
|
||||||
|
# incl. ten ~27.5 GiB Bagel loads); 60 min passed only ~1 in 3 runs
|
||||||
|
# even on main, and vLLM 0.25 weight loading needs ~10 min more.
|
||||||
|
timeout_in_minutes: 90
|
||||||
commands:
|
commands:
|
||||||
- pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and H100" --run-level "advanced_model"
|
- pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and H100" --run-level "advanced_model"
|
||||||
agents:
|
agents:
|
||||||
@@ -146,7 +149,9 @@ steps:
|
|||||||
type: DirectoryOrCreate
|
type: DirectoryOrCreate
|
||||||
|
|
||||||
- label: "Entrypoint Test with L4"
|
- label: "Entrypoint Test with L4"
|
||||||
timeout_in_minutes: 30
|
# 30 min left no headroom for a cold image pull (~11 min for new base
|
||||||
|
# layers) plus per-class engine relaunches; main passed at 26/30.
|
||||||
|
timeout_in_minutes: 45
|
||||||
commands:
|
commands:
|
||||||
- pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and L4" --run-level "advanced_model"
|
- pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and L4" --run-level "advanced_model"
|
||||||
agents:
|
agents:
|
||||||
|
|||||||
+1
-64
@@ -2,7 +2,7 @@
|
|||||||
# The pinned VLLM_PRECOMPILED_WHEEL_COMMIT and VLLM_BASE_TAG below must
|
# The pinned VLLM_PRECOMPILED_WHEEL_COMMIT and VLLM_BASE_TAG below must
|
||||||
# be updated on every rebase to match the new upstream vllm commit/tag.
|
# be updated on every rebase to match the new upstream vllm commit/tag.
|
||||||
ARG VLLM_BASE_IMAGE=vllm/vllm-openai
|
ARG VLLM_BASE_IMAGE=vllm/vllm-openai
|
||||||
ARG VLLM_BASE_TAG=v0.24.0
|
ARG VLLM_BASE_TAG=v0.25.0
|
||||||
FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
|
FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
|
||||||
ARG APP_DIR=/workspace/vllm-omni
|
ARG APP_DIR=/workspace/vllm-omni
|
||||||
WORKDIR ${APP_DIR}
|
WORKDIR ${APP_DIR}
|
||||||
@@ -14,71 +14,8 @@ RUN apt-get update && \
|
|||||||
apt-get clean && \
|
apt-get clean && \
|
||||||
rm -rf /var/lib/apt/lists/*
|
rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
|
|
||||||
# Install vLLM (CUDA 13.0 build) from precompiled wheel at the selected commit.
|
|
||||||
# Must use direct URL because the wheel has a PEP 440 local version identifier
|
|
||||||
# (e.g. +gaeee7ef93.cu130) which pip/uv refuse to install from a PEP 503 package index.
|
|
||||||
# The cu130 wheel index lives at /<commit>/cu130/vllm/ but the actual wheel files
|
|
||||||
# are stored at the top level /<commit>/<wheel>.
|
|
||||||
ENV VLLM_PRECOMPILED_WHEEL_COMMIT=dd10e03f95f94edbea1975c67ace3a35ec9a8a40
|
|
||||||
# Keep the base image's CUDA-12 toolkit libs on the loader path. NOTE: this does
|
|
||||||
# NOT resolve libnvJitLink.so.13 (that CUDA-13 lib is not in /usr/local/cuda here) —
|
|
||||||
# the .so.13 JIT linker is handled separately via ldconfig after the cu130 wheels
|
|
||||||
# are installed (see the nvidia-cuda-nvjitlink-cu13 step below).
|
|
||||||
ENV LD_LIBRARY_PATH=/usr/local/cuda/targets/x86_64-linux/lib:${LD_LIBRARY_PATH}
|
|
||||||
RUN VLLM_WHEEL_URL=$(python3 -c "import urllib.request,re; \
|
|
||||||
from urllib.parse import urljoin, quote; \
|
|
||||||
index_url='https://wheels.vllm.ai/${VLLM_PRECOMPILED_WHEEL_COMMIT}/cu130/vllm/'; \
|
|
||||||
html=urllib.request.urlopen(index_url).read().decode(); \
|
|
||||||
m=re.search(r'href=\"([^\"]*x86_64\.whl)\"',html); \
|
|
||||||
assert m, f'No x86_64 vLLM wheel found at {index_url}'; \
|
|
||||||
print(quote(urljoin(index_url,m.group(1)), safe=':/+%'))") && \
|
|
||||||
echo "Installing vLLM from: ${VLLM_WHEEL_URL}" && \
|
|
||||||
uv pip install --system --force-reinstall "${VLLM_WHEEL_URL}"
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
RUN uv pip install --system ".[dev]"
|
RUN uv pip install --system ".[dev]"
|
||||||
|
|
||||||
RUN uv pip install --system --upgrade \
|
|
||||||
"flashinfer-python==0.6.13" \
|
|
||||||
"flashinfer-cubin==0.6.13"
|
|
||||||
|
|
||||||
RUN uv pip install --system --upgrade \
|
|
||||||
"flashinfer-jit-cache==0.6.13" \
|
|
||||||
--index-url https://flashinfer.ai/whl/cu130
|
|
||||||
|
|
||||||
# Force-reinstall torch AFTER flashinfer, because flashinfer --upgrade pulls in
|
|
||||||
# a newer torch (2.12.x) whose libtorch_cuda.so lacks
|
|
||||||
# at::cuda::getCurrentCUDABlasHandle, causing "undefined symbol" at import time.
|
|
||||||
RUN uv pip install --system --force-reinstall \
|
|
||||||
"torch==2.11.0" "torchaudio==2.11.0" "torchvision==0.26.0" \
|
|
||||||
--torch-backend cu130
|
|
||||||
|
|
||||||
# CUDA 13 JIT linker: libnvJitLink.so.13 is provided by the nvidia-nvjitlink
|
|
||||||
# package that the cu130 torch/vllm wheels above pull into site-packages (the
|
|
||||||
# v0.24.0 base image's /usr/local/cuda toolkit is CUDA 12, so the LD_LIBRARY_PATH
|
|
||||||
# above never resolves the .so.13). Its lib dir is not on the dynamic-loader path,
|
|
||||||
# so bitsandbytes / torch.compile worker subprocesses fail to dlopen it. Locate the
|
|
||||||
# already-installed lib and register its dir with ldconfig (system-wide, survives
|
|
||||||
# subprocess env resets). Only fall back to the pip wheel (correct name:
|
|
||||||
# nvidia-nvjitlink-cu13, NOT nvidia-cuda-nvjitlink-cu13, which does not exist) if
|
|
||||||
# the torch deps did not bring it in.
|
|
||||||
RUN NVJITLINK_LIB="$(find / -name 'libnvJitLink.so.13*' 2>/dev/null | head -1)" && \
|
|
||||||
if [ -z "$NVJITLINK_LIB" ]; then \
|
|
||||||
uv pip install --system "nvidia-nvjitlink-cu13" && \
|
|
||||||
NVJITLINK_LIB="$(find / -name 'libnvJitLink.so.13*' 2>/dev/null | head -1)"; \
|
|
||||||
fi && \
|
|
||||||
test -n "$NVJITLINK_LIB" && \
|
|
||||||
dirname "$NVJITLINK_LIB" > /etc/ld.so.conf.d/nvjitlink-cu13.conf && \
|
|
||||||
ldconfig && \
|
|
||||||
echo "Registered ${NVJITLINK_LIB} with ldconfig"
|
|
||||||
|
|
||||||
# Re-pin numpy LAST. numba requires numpy <= 2.4, but the flashinfer and torch cu130
|
|
||||||
# reinstalls above resolve numpy back up to 2.5, which breaks `import numba` at test
|
|
||||||
# time ("Numba needs NumPy 2.4 or less"). This must be the final dependency op so
|
|
||||||
# nothing can clobber it again.
|
|
||||||
RUN uv pip install --system "numpy==2.2.6"
|
|
||||||
|
|
||||||
RUN ln -sf /usr/bin/python3 /usr/bin/python
|
RUN ln -sf /usr/bin/python3 /usr/bin/python
|
||||||
|
|
||||||
|
|||||||
@@ -34,7 +34,7 @@ vLLM-Omni is a Python library that supports the following GPU variants. The libr
|
|||||||
|
|
||||||
### Pre-built wheels
|
### Pre-built wheels
|
||||||
|
|
||||||
Note: Pre-built wheels are currently available for vLLM-Omni 0.11.0rc1, 0.12.0rc1, 0.14.0rc1, 0.14.0, 0.16.0, 0.18.0, 0.20.0, 0.21.0, 0.22.0, 0.23.0, and 0.24.0. If you need a newer unreleased revision, please [build from source](https://docs.vllm.ai/projects/vllm-omni/en/latest/getting_started/installation/gpu/#build-wheel-from-source).
|
Note: Pre-built wheels are currently available for vLLM-Omni 0.11.0rc1, 0.12.0rc1, 0.14.0rc1, 0.14.0, 0.16.0, 0.18.0, 0.20.0, 0.21.0, 0.22.0, 0.23.0, 0.24.0, and 0.25.0. If you need a newer unreleased revision, please [build from source](https://docs.vllm.ai/projects/vllm-omni/en/latest/getting_started/installation/gpu/#build-wheel-from-source).
|
||||||
|
|
||||||
=== "NVIDIA CUDA"
|
=== "NVIDIA CUDA"
|
||||||
|
|
||||||
|
|||||||
@@ -20,7 +20,7 @@ Therefore, it is recommended to install vLLM and vLLM-Omni with a **fresh new**
|
|||||||
|
|
||||||
vLLM-Omni is built based on vLLM. Please install it with command below.
|
vLLM-Omni is built based on vLLM. Please install it with command below.
|
||||||
```bash
|
```bash
|
||||||
uv pip install vllm==0.24.0 --torch-backend=auto
|
uv pip install vllm==0.25.0 --torch-backend=auto
|
||||||
```
|
```
|
||||||
|
|
||||||
#### Installation of vLLM-Omni
|
#### Installation of vLLM-Omni
|
||||||
@@ -39,13 +39,13 @@ uv pip install 'vllm-omni[demo]'
|
|||||||
# --8<-- [start:build-wheel-from-source]
|
# --8<-- [start:build-wheel-from-source]
|
||||||
|
|
||||||
#### Installation of vLLM
|
#### Installation of vLLM
|
||||||
If you do not need to modify source code of vLLM, you can directly install the stable 0.24.0 release version of the library
|
If you do not need to modify source code of vLLM, you can directly install the stable 0.25.0 release version of the library
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
uv pip install vllm==0.24.0 --torch-backend=auto
|
uv pip install vllm==0.25.0 --torch-backend=auto
|
||||||
```
|
```
|
||||||
|
|
||||||
The 0.24.0 release of vLLM ships CUDA 13.0-compatible binaries by default. If you need a different CUDA variant or want to reuse an existing PyTorch installation, build vLLM from source instead.
|
The 0.25.0 release of vLLM ships CUDA 13.0-compatible binaries by default. If you need a different CUDA variant or want to reuse an existing PyTorch installation, build vLLM from source instead.
|
||||||
|
|
||||||
#### Installation of vLLM-Omni
|
#### Installation of vLLM-Omni
|
||||||
Since vllm-omni is rapidly evolving, it's recommended to install it from source
|
Since vllm-omni is rapidly evolving, it's recommended to install it from source
|
||||||
@@ -66,12 +66,12 @@ If you want to check, modify or debug with source code of vLLM, install the libr
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/vllm-project/vllm.git
|
git clone https://github.com/vllm-project/vllm.git
|
||||||
cd vllm
|
cd vllm
|
||||||
git checkout v0.24.0
|
git checkout v0.25.0
|
||||||
```
|
```
|
||||||
Set up environment variables to get pre-built wheels. If there are internet problems, just download the whl file manually. And set `VLLM_PRECOMPILED_WHEEL_LOCATION` as your local absolute path of whl file.
|
Set up environment variables to get pre-built wheels. If there are internet problems, just download the whl file manually. And set `VLLM_PRECOMPILED_WHEEL_LOCATION` as your local absolute path of whl file.
|
||||||
```bash
|
```bash
|
||||||
#For CUDA 13.0 (the default for v0.24.0; the wheel filename has no `+cu130` suffix)
|
#For CUDA 13.0 (the default for v0.25.0; the wheel filename has no `+cu130` suffix)
|
||||||
export VLLM_PRECOMPILED_WHEEL_LOCATION=https://github.com/vllm-project/vllm/releases/download/v0.24.0/vllm-0.24.0-cp38-abi3-manylinux_2_28_x86_64.whl
|
export VLLM_PRECOMPILED_WHEEL_LOCATION=https://github.com/vllm-project/vllm/releases/download/v0.25.0/vllm-0.25.0-cp38-abi3-manylinux_2_28_x86_64.whl
|
||||||
```
|
```
|
||||||
Install vllm with command below (If you have no existing PyTorch).
|
Install vllm with command below (If you have no existing PyTorch).
|
||||||
```bash
|
```bash
|
||||||
@@ -102,7 +102,7 @@ docker run --runtime nvidia --gpus 2 \
|
|||||||
--env "HF_TOKEN=$HF_TOKEN" \
|
--env "HF_TOKEN=$HF_TOKEN" \
|
||||||
-p 8091:8091 \
|
-p 8091:8091 \
|
||||||
--ipc=host \
|
--ipc=host \
|
||||||
vllm/vllm-omni:v0.24.0 \
|
vllm/vllm-omni:v0.25.0 \
|
||||||
vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
|
vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|||||||
@@ -13,7 +13,7 @@ vLLM-Omni current recommends the steps in under setup through Docker Images.
|
|||||||
|
|
||||||
vLLM-Omni is built based on vLLM. Please install it with command below.
|
vLLM-Omni is built based on vLLM. Please install it with command below.
|
||||||
```bash
|
```bash
|
||||||
uv pip install vllm==0.24.0+rocm722 --extra-index-url https://wheels.vllm.ai/rocm/0.24.0/rocm722
|
uv pip install vllm==0.25.0+rocm723 --extra-index-url https://wheels.vllm.ai/rocm/0.25.0/rocm723
|
||||||
```
|
```
|
||||||
|
|
||||||
#### Installation of vLLM-Omni
|
#### Installation of vLLM-Omni
|
||||||
@@ -34,13 +34,13 @@ uv pip install onnxruntime-rocm
|
|||||||
# --8<-- [start:build-wheel-from-source]
|
# --8<-- [start:build-wheel-from-source]
|
||||||
|
|
||||||
#### Installation of vLLM
|
#### Installation of vLLM
|
||||||
If you do not need to modify source code of vLLM, you can directly install the stable 0.24.0 release version of the library
|
If you do not need to modify source code of vLLM, you can directly install the stable 0.25.0 release version of the library
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
uv pip install vllm==0.24.0+rocm722 --extra-index-url https://wheels.vllm.ai/rocm/0.24.0/rocm722
|
uv pip install vllm==0.25.0+rocm723 --extra-index-url https://wheels.vllm.ai/rocm/0.25.0/rocm723
|
||||||
```
|
```
|
||||||
|
|
||||||
The pre-built 0.24.0 vLLM wheel targets ROCm 7.2.2. If you need a different ROCm stack or want to reuse an existing PyTorch installation, build vLLM from source instead.
|
The pre-built 0.25.0 vLLM wheel targets ROCm 7.2.3. If you need a different ROCm stack or want to reuse an existing PyTorch installation, build vLLM from source instead.
|
||||||
|
|
||||||
#### Installation of vLLM-Omni
|
#### Installation of vLLM-Omni
|
||||||
Since vllm-omni is rapidly evolving, it's recommended to install it from source
|
Since vllm-omni is rapidly evolving, it's recommended to install it from source
|
||||||
@@ -58,7 +58,7 @@ If you want to check, modify or debug with source code of vLLM, install the libr
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/vllm-project/vllm.git
|
git clone https://github.com/vllm-project/vllm.git
|
||||||
cd vllm
|
cd vllm
|
||||||
git checkout v0.24.0
|
git checkout v0.25.0
|
||||||
python3 -m pip install -r requirements/rocm.txt
|
python3 -m pip install -r requirements/rocm.txt
|
||||||
python3 setup.py develop
|
python3 setup.py develop
|
||||||
```
|
```
|
||||||
@@ -130,7 +130,7 @@ docker run --rm \
|
|||||||
-v ~/.cache/huggingface:/root/.cache/huggingface \
|
-v ~/.cache/huggingface:/root/.cache/huggingface \
|
||||||
--env "HF_TOKEN=$HF_TOKEN" \
|
--env "HF_TOKEN=$HF_TOKEN" \
|
||||||
-p 8091:8091 \
|
-p 8091:8091 \
|
||||||
vllm/vllm-omni-rocm:v0.24.0 \
|
vllm/vllm-omni-rocm:v0.25.0 \
|
||||||
--model Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
|
--model Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
|
||||||
```
|
```
|
||||||
|
|
||||||
@@ -149,7 +149,7 @@ docker run --rm -it \
|
|||||||
-v ~/.cache/huggingface:/root/.cache/huggingface \
|
-v ~/.cache/huggingface:/root/.cache/huggingface \
|
||||||
--env "HF_TOKEN=$HF_TOKEN" \
|
--env "HF_TOKEN=$HF_TOKEN" \
|
||||||
--entrypoint bash \
|
--entrypoint bash \
|
||||||
vllm/vllm-omni-rocm:v0.24.0
|
vllm/vllm-omni-rocm:v0.25.0
|
||||||
```
|
```
|
||||||
|
|
||||||
# --8<-- [end:pre-built-images]
|
# --8<-- [end:pre-built-images]
|
||||||
@@ -19,10 +19,10 @@ uv venv --python 3.12 --seed
|
|||||||
source .venv/bin/activate
|
source .venv/bin/activate
|
||||||
|
|
||||||
# On CUDA
|
# On CUDA
|
||||||
uv pip install vllm==0.24.0 --torch-backend=auto
|
uv pip install vllm==0.25.0 --torch-backend=auto
|
||||||
|
|
||||||
# On ROCm
|
# On ROCm
|
||||||
uv pip install vllm==0.24.0+rocm722 --extra-index-url https://wheels.vllm.ai/rocm/0.24.0/rocm722
|
uv pip install vllm==0.25.0+rocm723 --extra-index-url https://wheels.vllm.ai/rocm/0.25.0/rocm723
|
||||||
|
|
||||||
git clone https://github.com/vllm-project/vllm-omni.git
|
git clone https://github.com/vllm-project/vllm-omni.git
|
||||||
cd vllm-omni
|
cd vllm-omni
|
||||||
@@ -34,7 +34,7 @@ For additional installation methods — please see the [installation guide](inst
|
|||||||
!!! note
|
!!! note
|
||||||
It is important to install the same major & minor version of vLLM and vLLM Omni, otherwise things may not work as expected. If the versions are misaligned, you will see a warning when you import vLLM Omni.
|
It is important to install the same major & minor version of vLLM and vLLM Omni, otherwise things may not work as expected. If the versions are misaligned, you will see a warning when you import vLLM Omni.
|
||||||
|
|
||||||
If you are seeing strange behavior with the `vllm` command not handling the `--omni` flag correctly, you most likely have a version mismatch with vLLM < `0.24.0` and vLLM Omni `0.24.0`, as vLLM Omni no longer hijacks the vLLM entrypoint. Updating vLLM should resolve this issue.
|
If you are seeing strange behavior with the `vllm` command not handling the `--omni` flag correctly, you most likely have a version mismatch with vLLM < `0.25.0` and vLLM Omni `0.25.0`, as vLLM Omni no longer hijacks the vLLM entrypoint. Updating vLLM should resolve this issue.
|
||||||
|
|
||||||
## Offline Inference
|
## Offline Inference
|
||||||
|
|
||||||
|
|||||||
Reference in new issue
Block a user