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>
11 lines
260 B
Plaintext
11 lines
260 B
Plaintext
# Diffusion / image / video / extra-audio deps (not needed by AR-only edge builds).
|
|
diffusers==0.40.0
|
|
kernels==0.15.2
|
|
cache-dit==1.5.0
|
|
torchsde>=0.2.6
|
|
openai-whisper>=20250625
|
|
imageio[ffmpeg]>=2.37.2
|
|
x-transformers>=2.12.2
|
|
gguf>=0.10.0
|
|
cosmos-guardrail>=0.3.1
|