aa41a3ac97
Signed-off-by: Armaan Amatya <armaanamatya2014@gmail.com> Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
50 lines
2.0 KiB
Plaintext
50 lines
2.0 KiB
Plaintext
# Common dependencies for all platforms
|
|
# kernels==0.16.1 requires the LayerRepository version=/revision= integration
|
|
# introduced in transformers 5.13. Keep the tested upper bound: 5.15 has
|
|
# a reported model-construction regression; later versions need validation.
|
|
# This range also satisfies vLLM 0.30.0's transformers>=5.10.4 requirement.
|
|
# MOSS-TTS-Nano's list/set weight-loading compatibility is handled by
|
|
# transformers_keys_to_ignore_compat in model_executor/models/utils.py.
|
|
transformers >= 5.13.0, < 5.15
|
|
av>=14.0.0
|
|
# typing_extensions.Concatenate accepts a trailing `...` on 3.10 only from
|
|
# 4.13 (older 4.12.x re-export typing.Concatenate, which rejects it). The
|
|
# Nemotron VoiceChat codec annotates `Concatenate[int, ...]`, so pin the
|
|
# floor instead of relying on the version vLLM/torch pull transitively.
|
|
typing_extensions>=4.13
|
|
omegaconf>=2.3.0
|
|
diffusers==0.40.0
|
|
# Hub kernels, including LTX-2.5 NATTEN. 0.16+ resolves torch-stable-abi*
|
|
# FA3 builds on torch 2.13 / cu130; keep in sync with transformers above.
|
|
kernels==0.16.1
|
|
safetensors>=0.8.0
|
|
accelerate==1.12.0
|
|
soundfile>=0.13.1
|
|
# Breeze reference conditioning must use the released codec's soxr resampling.
|
|
soxr>=0.5.0.post1
|
|
cache-dit==1.5.0
|
|
tqdm>=4.66.0
|
|
torchsde>=0.2.6
|
|
openai-whisper>=20250625
|
|
imageio[ffmpeg]>=2.37.2
|
|
x-transformers>=2.12.2
|
|
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
|
|
# Required for GGUF-quantized diffusion model loading (gguf_adapters). The CI
|
|
# base image does not ship it, so declare it explicitly. The loader also guards
|
|
# this import so a missing gguf no longer breaks all diffusion model loading.
|
|
gguf>=0.10.0
|
|
# Required for running the Cosmos3 model with guardrails enabled (default behavior).
|
|
cosmos-guardrail>=0.3.1
|
|
# Required for CosyVoice3 (get_window/resample_poly). >=1.18.0 requires
|
|
# Python >=3.12, breaking base installs on the project's supported 3.10/3.11;
|
|
# these are long-stable APIs with no version-specific need for 1.18.
|
|
scipy>=1.11.0
|
|
s3tokenizer==0.3.0
|