anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI][XPU]switch to use vLLM base docker for XPU (#6727)

Browse Source 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
This commit is contained in:
Chendi.Xue authored and GitHub committed 2026-08-29 09:03:00 +08:00
1 parent 8bfad23f98
commit 034af1f657
5 files changed
+88 -150
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/intel/pipeline-intel.yml
+1 -1
View File
@@ -10,7 +10,7 @@ steps:
DOCKER_BUILDKIT: "1"
# Buildkite will automatically replace this with the actual commit hash
VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
VLLM_VERSION: "v0.27.0"
VLLM_VERSION: "v0.28.0"
priority: 100
timeout_in_minutes: 60
soft_fail: false
.buildkite/intel/scripts/run-xpu-test.sh
+36 -4
View File
@@ -5,7 +5,12 @@ set -ex
omni_source_dir=$(git rev-parse --show-toplevel)
base_image_name="xpu/vllm-omni-ci-base:${VLLM_VERSION:?VLLM_VERSION must be set}"
: "${VLLM_VERSION:?VLLM_VERSION must be set}"
# Official upstream XPU image. It is published from vllm's own
# docker/Dockerfile.xpu, which is exactly what build_vllm_base() clones and
# builds below, so pulling it is equivalent to building the fallback base.
upstream_base_image="vllm/vllm-openai-xpu:${VLLM_VERSION}"
local_base_image="xpu/vllm-omni-ci-base:${VLLM_VERSION}"
image_name="xpu/vllm-omni-ci:${BUILDKITE_COMMIT:?BUILDKITE_COMMIT must be set}"
container_name="xpu_${BUILDKITE_COMMIT}_$(
tr -dc A-Za-z0-9 </dev/urandom | head -c 10
@@ -49,9 +54,36 @@ build_vllm_base() (
"${vllm_source_dir}"
)
if [ -z "$(docker images -q "${base_image_name}")" ]; then
build_vllm_base
fi
# Resolve the vLLM base image, in priority order:
# 1. the published upstream image for VLLM_VERSION, pulled fresh (so moving
# tags like nightly are refreshed rather than served stale from disk);
# 2. a local copy of that same image, when the registry is unreachable;
# 3. VLLM_BASE, if that image is already on disk;
# 4. otherwise build VLLM_BASE from the matching vLLM source tag (~30min).
# VLLM_BASE names the fallback base and defaults to ${local_base_image}; set it
# to reuse or produce a base under a different tag.
resolve_vllm_base() {
if docker pull "${upstream_base_image}"; then
base_image_name="${upstream_base_image}"
return
fi
# Registry unreachable, but a previous run may have left the image behind.
if [ -n "$(docker images -q "${upstream_base_image}")" ]; then
echo "WARNING: could not pull ${upstream_base_image}; using local copy" >&2
base_image_name="${upstream_base_image}"
return
fi
echo "WARNING: ${upstream_base_image} unavailable remotely and locally" >&2
base_image_name="${VLLM_BASE:-${local_base_image}}"
if [ -z "$(docker images -q "${base_image_name}")" ]; then
echo "WARNING: building ${base_image_name} from vLLM ${VLLM_VERSION} source" >&2
build_vllm_base
fi
}
resolve_vllm_base
# Try building the docker image
docker_build "${image_name}" --build-arg "VLLM_BASE=${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}"
docker/Dockerfile.xpu
+27 -134
View File
@@ -1,140 +1,33 @@
# Argument to configure vllm base image if pre-built
ARG VLLM_BASE=vllm-base
FROM intel/deep-learning-essentials:2025.3.2-0-devel-ubuntu24.04 AS vllm-base
WORKDIR /workspace/
ARG PYTHON_VERSION=3.12
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/xpu"
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \
echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list
RUN apt clean && apt-get update -y && \
apt-get install -y --no-install-recommends --fix-missing \
curl \
ffmpeg \
git \
libsndfile1 \
libsm6 \
libxext6 \
libgl1 \
lsb-release \
libaio-dev \
numactl \
wget \
vim \
python3.12 \
python3.12-dev \
python3-pip
# Add oneAPI repo, pin oneAPI to 2025.3, then install pinned packages in one layer.
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \
echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && \
printf '%s\n' \
'Package: intel-oneapi-* intel-deep-learning-essentials* intel-pti*' \
'Pin: version 2025.3*' \
'Pin-Priority: 1001' \
> /etc/apt/preferences.d/oneapi-2025.3.pref && \
apt-get update -y && \
apt-get install -y --no-install-recommends \
intel-oneapi-compiler-dpcpp-cpp-2025.3 \
intel-oneapi-mkl-devel-2025.3 \
intel-oneapi-dnnl-devel-2025.3 && \
rm -rf /var/lib/apt/lists/*
# Install UMD with fixed version
RUN mkdir neo && \
cd neo && \
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.24.8/intel-igc-core-2_2.24.8+20344_amd64.deb && \
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.24.8/intel-igc-opencl-2_2.24.8+20344_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/intel-ocloc_25.48.36300.8-0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/intel-opencl-icd_25.48.36300.8-0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/libigdgmm12_22.8.2_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/libze-intel-gpu1_25.48.36300.8-0_amd64.deb && \
wget https://github.com/oneapi-src/level-zero/releases/download/v1.26.0/level-zero_1.26.0+u24.04_amd64.deb && \
dpkg -i *.deb && \
cd .. && \
rm -rf neo
ENV PATH="/root/.local/bin:$PATH"
ENV VIRTUAL_ENV="/opt/venv"
ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
ENV PATH="$VIRTUAL_ENV/bin:$PATH"
# This oneccl contains the BMG support which is not the case for default version of oneapi 2025.3.
ARG ONECCL_INSTALLER="intel-oneccl-2021.15.9.14_offline.sh"
RUN wget "https://github.com/uxlfoundation/oneCCL/releases/download/2021.15.9/${ONECCL_INSTALLER}" && \
bash "${ONECCL_INSTALLER}" -a --silent --eula accept && \
rm "${ONECCL_INSTALLER}" && \
echo "source /opt/intel/oneapi/setvars.sh --force" >> /root/.bashrc && \
echo "source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force" >> /root/.bashrc
RUN rm -f /opt/intel/oneapi/ccl/latest && \
ln -s /opt/intel/oneapi/ccl/2021.15 /opt/intel/oneapi/ccl/latest
SHELL ["bash", "-c"]
CMD ["bash", "-c", "source /root/.bashrc && exec bash"]
WORKDIR /workspace/
ENV UV_HTTP_TIMEOUT=500
# Configure package index for XPU
ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
ENV UV_INDEX_STRATEGY="unsafe-best-match"
ENV UV_LINK_MODE="copy"
ARG VLLM_VERSION=v0.27.0
RUN git clone -b ${VLLM_VERSION} https://github.com/vllm-project/vllm
WORKDIR /workspace/vllm
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --upgrade pip && \
uv pip install -r requirements/xpu.txt && \
uv pip install setuptools_scm &&\
uv pip install grpcio-tools protobuf nanobind && \
source /opt/intel/oneapi/setvars.sh --force && \
source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force && \
export CMAKE_PREFIX_PATH="$(python3 -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH}"
ENV LD_LIBRARY_PATH="/opt/intel/oneapi/ccl/2021.15/lib:$LD_LIBRARY_PATH:/usr/local/lib/"
ENV VLLM_TARGET_DEVICE=xpu
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip uninstall triton triton-xpu && \
uv pip install triton-xpu==3.7.2 && \
uv pip install --no-build-isolation --no-deps .
CMD ["/bin/bash"]
FROM vllm-base AS vllm-openai
# install nixl from source code
RUN uv pip install nixl
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope
# install development dependencies (for testing)
RUN uv pip install -e tests/vllm_test_utils
# ensure vllm is properly installed
RUN python -c "import vllm, inspect; print(vllm.__file__)"
RUN uv pip show vllm
CMD ["/bin/bash"]
ENTRYPOINT []
# Target vLLM version: v0.28.0. Keep VLLM_VERSION aligned with the target vLLM
# release on every rebase.
#
# This file layers vLLM-Omni on top of the published upstream XPU image, which
# already ships a self-consistent XPU runtime (torch-xpu, oneCCL/UCX+NIXL, the
# pinned UMD/compute-runtime stack, and vLLM itself) built from
# https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile.xpu. Docker
# pulls that base automatically, so there is nothing to build here beyond the
# Omni layers. Mirrors how docker/Dockerfile.ci consumes vllm/vllm-openai.
#
# If the tag does not exist yet (targeting an unreleased vLLM commit), build the
# base from upstream's own Dockerfile and point VLLM_BASE at the result:
#
# git clone --depth 1 --branch $VLLM_VERSION https://github.com/vllm-project/vllm /tmp/vllm
# docker build -t vllm-openai-xpu:local --target vllm-openai \
# -f /tmp/vllm/docker/Dockerfile.xpu /tmp/vllm
# docker build -f docker/Dockerfile.xpu --build-arg VLLM_BASE=vllm-openai-xpu:local .
#
# .buildkite/intel/scripts/run-xpu-test.sh automates that pull-then-build fallback.
ARG VLLM_BASE_IMAGE=vllm/vllm-openai-xpu
ARG VLLM_VERSION=v0.28.0
ARG VLLM_BASE=${VLLM_BASE_IMAGE}:${VLLM_VERSION}
FROM ${VLLM_BASE} AS vllm-omni
# The base image ships ENTRYPOINT ["vllm", "serve"]; clear it so this stage stays
# usable as a plain shell/test container regardless of which VLLM_BASE was used.
ENTRYPOINT []
CMD ["/bin/bash"]
RUN apt-get update && \
apt-get install -y espeak-ng ffmpeg git jq && \
apt-get clean && \
docs/getting_started/installation/gpu/xpu.inc.md
+13
View File
@@ -23,6 +23,19 @@ vLLM-Omni currently recommends using the Docker image setup steps below.
DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile.xpu -t vllm-omni-xpu --shm-size=4g .
```
This layers vLLM-Omni on top of the published `vllm/vllm-openai-xpu:<VLLM_VERSION>`
base image, which Docker pulls automatically. To target a different vLLM release,
pass `--build-arg VLLM_VERSION=<tag>`. If that tag has not been published yet, build
the base from upstream's own Dockerfile first and point the build at it:
```bash
git clone --depth 1 --branch "$VLLM_VERSION" https://github.com/vllm-project/vllm /tmp/vllm
DOCKER_BUILDKIT=1 docker build -t vllm-openai-xpu:local --target vllm-openai \
-f /tmp/vllm/docker/Dockerfile.xpu /tmp/vllm
DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile.xpu -t vllm-omni-xpu --shm-size=4g \
--build-arg VLLM_BASE=vllm-openai-xpu:local .
```
#### Launch the docker image
##### Launch with OpenAI API Server
docs/models/supported_models.md
+11 -11
View File
@@ -26,15 +26,15 @@ th {
| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | | — |
| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | | — |
| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen-Image) |
| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen-Image-2512.md) |
| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | | | ✅︎ | [Published](https://recipes.vllm.ai/Qwen/Qwen-Image) |
| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | | | ✅︎ | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen-Image-2512.md) |
| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | | — |
| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | | — |
| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | ✅︎ | — |
| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `LingBotWorldCausalDMDPipeline` | LingBot-World 2.0 v1 (experimental) | `robbyant/lingbot-world-v2-14b-causal-fast-diffusers` | Experimental | | | | — |
@@ -42,7 +42,7 @@ th {
| `SanaWmPipeline` | SANA-WM | `BBBBruce/SANA-WM_bidirectional-stage1-diffusers` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/NVIDIA/SANA-WM.md) |
| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ | | | | — |
| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ | | | ✅︎ | — |
| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | | — |
| `LTX2TwoStagePipeline` | LTX-2 / LTX-2.3 ordinary two-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` + matching Lightricks LoRA and upsampler | ✅︎ | ✅︎ | | | — |
| `LTX2DistilledOneStagePipeline` | LTX-2 / LTX-2.3 merged-distilled one-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled`, `diffusers/LTX-2.3-Distilled-Diffusers` | ✅︎ | ✅︎ | | | — |
@@ -62,12 +62,12 @@ th {
| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `LongCatVideoAvatarPipeline` | LongCat-Video-Avatar-1.5 A2V/AI2V (native single-speaker and multi-speaker AI2V/AVC) | `meituan-longcat/LongCat-Video-Avatar-1.5` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/meituan-longcat/LongCat-Video-Avatar-1.5.md) |
| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | | — |
| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | ✅︎ | — |
| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ | — |
| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ | — |
| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | | — |
| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | | — |
| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | ✅︎ | — |
| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | ✅︎ | — |
| `DotsTTSForConditionalGeneration` | dots.tts | `rednote-hilab/dots.tts-soar` | ✅︎ | | | | — |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | | — |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | | — |
@@ -78,10 +78,10 @@ th {
| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ | — |
| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ | — |
| `MiniMaxMusic3ForConditionalGeneration` | MiniMax Music 3 (text-to-music) | `MiniMaxAI/MiniMax-Music3` | ✅︎ | | | | — |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | | | ✅︎ | [Published](https://recipes.vllm.ai/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | | — |
| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | ✅︎ | — |
| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | | — |
| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | | — |
| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | | — |
@@ -101,10 +101,10 @@ th {
| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | | — |
| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | | — |
| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | | — |
|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | | — |
|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | ✅︎ | — |
| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | | — |
| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `GepardTalkerForConditionalGeneration` | Gepard-1.0 | `nineninesix/gepard-1.0` | ✅︎ | | | | — |
| `GepardTalkerForConditionalGeneration` | Gepard-1.0 | `nineninesix/gepard-1.0` | ✅︎ | | | ✅︎ | — |
|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | | — |
| `HiDreamO1ImagePipeline` | HiDream-O1-Image | `HiDream-ai/HiDream-O1-Image` | ✅︎ | | | | — |