tzhouamandClaude Fable 5.1
8e912db6c8
* diffusers is no longer imported by vllm_omni.diffusion.data (annotation only); vllm_omni.diffusion.io_support (diffusion registry + distributed state) is imported lazily by config_factory and async_omni_engine, so constructing a Qwen3-TTS pipeline config / AsyncOmni no longer loads diffusers, x_transformers or whisper (guarded by tests/config/test_import_guard.py). * requirements/common.txt = core.txt (AR/speech runtime) + media.txt (diffusion/video/extra audio); VLLM_OMNI_EDGE_BUILD=1 makes setup.py use requirements/<device>-edge.txt (core only); `edge` extra adds websockets and sounddevice for on-device clients. Measured on this host (CUDA venv): `import vllm` 7.0-7.9 s, `import vllm_omni` adds ~20 s of which ~17 s is transformers' own import (transformers.utils.import_utils) pulled in by vllm_omni.patch / vllm_omni.version; that floor is not vLLM-Omni's and is unchanged. Guard test: no diffusion module loaded on the TTS path. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
18 lines
398 B
Plaintext
18 lines
398 B
Plaintext
# Core runtime deps for AR / generation (TTS, speech) pipelines. Media /
|
|
# diffusion / video deps live in media.txt; common.txt pulls both.
|
|
transformers >= 5.10.1, < 5.15
|
|
av>=14.0.0
|
|
omegaconf>=2.3.0
|
|
safetensors>=0.8.0
|
|
accelerate==1.12.0
|
|
soundfile>=0.13.1
|
|
tqdm>=4.66.0
|
|
einops>=0.8.1
|
|
prettytable>=3.8.0
|
|
aenum==3.1.16
|
|
pyzmq>=25.0.0
|
|
janus>=1.0.0
|
|
msgpack>=1.0.0
|
|
pydantic>=2.1.0
|
|
pydantic-settings>=2.0.0
|