Silence vLLM server in a better way (theres an arg for that!)

environment_neusv.yml

@@ -1,229 +0,0 @@
-name: neusv-public-1
-channels:
-  - pytorch
-  - nvidia
-  - conda-forge
-dependencies:
-  - _libgcc_mutex=0.1=conda_forge
-  - _openmp_mutex=4.5=2_kmp_llvm
-  - aom=3.6.1=h59595ed_0
-  - blas=2.116=mkl
-  - blas-devel=3.9.0=16_linux64_mkl
-  - brotli-python=1.1.0=py310hf71b8c6_2
-  - bzip2=1.0.8=h4bc722e_7
-  - ca-certificates=2024.8.30=hbcca054_0
-  - certifi=2024.8.30=pyhd8ed1ab_0
-  - cffi=1.17.1=py310h8deb56e_0
-  - charset-normalizer=3.4.0=pyhd8ed1ab_1
-  - cpython=3.10.16=py310hd8ed1ab_1
-  - cuda-cudart=12.4.127=0
-  - cuda-cupti=12.4.127=0
-  - cuda-libraries=12.4.1=0
-  - cuda-nvrtc=12.4.127=0
-  - cuda-nvtx=12.4.127=0
-  - cuda-opencl=12.6.77=0
-  - cuda-runtime=12.4.1=0
-  - cuda-version=12.6=3
-  - ffmpeg=4.4.2=gpl_hdf48244_113
-  - filelock=3.16.1=pyhd8ed1ab_1
-  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
-  - font-ttf-inconsolata=3.000=h77eed37_0
-  - font-ttf-source-code-pro=2.038=h77eed37_0
-  - font-ttf-ubuntu=0.83=h77eed37_3
-  - fontconfig=2.15.0=h7e30c49_1
-  - fonts-conda-ecosystem=1=0
-  - fonts-conda-forge=1=0
-  - freetype=2.12.1=h267a509_2
-  - gettext=0.22.5=he02047a_3
-  - gettext-tools=0.22.5=he02047a_3
-  - giflib=5.2.2=hd590300_0
-  - gmp=6.3.0=hac33072_2
-  - gmpy2=2.1.5=py310he8512ff_3
-  - gnutls=3.7.9=hb077bed_0
-  - h2=4.1.0=pyhd8ed1ab_1
-  - hpack=4.0.0=pyhd8ed1ab_1
-  - hyperframe=6.0.1=pyhd8ed1ab_1
-  - idna=3.10=pyhd8ed1ab_1
-  - jinja2=3.1.4=pyhd8ed1ab_1
-  - lame=3.100=h166bdaf_1003
-  - lcms2=2.16=hb7c19ff_0
-  - ld_impl_linux-64=2.43=h712a8e2_2
-  - lerc=4.0.0=h27087fc_0
-  - libasprintf=0.22.5=he8f35ee_3
-  - libasprintf-devel=0.22.5=he8f35ee_3
-  - libblas=3.9.0=16_linux64_mkl
-  - libcblas=3.9.0=16_linux64_mkl
-  - libcublas=12.4.5.8=0
-  - libcufft=11.2.1.3=0
-  - libcufile=1.11.1.6=0
-  - libcurand=10.3.7.77=0
-  - libcusolver=11.6.1.9=0
-  - libcusparse=12.3.1.170=0
-  - libdeflate=1.22=hb9d3cd8_0
-  - libdrm=2.4.124=hb9d3cd8_0
-  - libegl=1.7.0=ha4b6fd6_2
-  - libexpat=2.6.4=h5888daf_0
-  - libffi=3.4.2=h7f98852_5
-  - libgcc=14.2.0=h77fa898_1
-  - libgcc-ng=14.2.0=h69a702a_1
-  - libgettextpo=0.22.5=he02047a_3
-  - libgettextpo-devel=0.22.5=he02047a_3
-  - libgfortran=14.2.0=h69a702a_1
-  - libgfortran-ng=14.2.0=h69a702a_1
-  - libgfortran5=14.2.0=hd5240d6_1
-  - libgl=1.7.0=ha4b6fd6_2
-  - libglvnd=1.7.0=ha4b6fd6_2
-  - libglx=1.7.0=ha4b6fd6_2
-  - libgomp=14.2.0=h77fa898_1
-  - libhwloc=2.11.2=default_h0d58e46_1001
-  - libiconv=1.17=hd590300_2
-  - libidn2=2.3.7=hd590300_0
-  - libjpeg-turbo=3.0.0=hd590300_1
-  - liblapack=3.9.0=16_linux64_mkl
-  - liblapacke=3.9.0=16_linux64_mkl
-  - liblzma=5.6.3=hb9d3cd8_1
-  - libnpp=12.2.5.30=0
-  - libnsl=2.0.1=hd590300_0
-  - libnvfatbin=12.6.77=0
-  - libnvjitlink=12.4.127=0
-  - libnvjpeg=12.3.1.117=0
-  - libpciaccess=0.18=hd590300_0
-  - libpng=1.6.44=hadc24fc_0
-  - libsqlite=3.47.0=hadc24fc_1
-  - libstdcxx=14.2.0=hc0a3c3a_1
-  - libstdcxx-ng=14.2.0=h4852527_1
-  - libtasn1=4.19.0=h166bdaf_0
-  - libtiff=4.7.0=hc4654cb_2
-  - libunistring=0.9.10=h7f98852_0
-  - libuuid=2.38.1=h0b41bf4_0
-  - libva=2.22.0=h8a09558_1
-  - libvpx=1.13.1=h59595ed_0
-  - libwebp=1.4.0=h2c329e2_0
-  - libwebp-base=1.4.0=hd590300_0
-  - libxcb=1.17.0=h8a09558_0
-  - libxcrypt=4.4.36=hd590300_1
-  - libxml2=2.13.5=h0d44e9d_1
-  - libzlib=1.3.1=hb9d3cd8_2
-  - llvm-openmp=15.0.7=h0cdce71_0
-  - mkl=2022.1.0=h84fe81f_915
-  - mkl-devel=2022.1.0=ha770c72_916
-  - mkl-include=2022.1.0=h84fe81f_915
-  - mpc=1.3.1=h24ddda3_1
-  - mpfr=4.2.1=h90cbb55_3
-  - mpmath=1.3.0=pyhd8ed1ab_1
-  - ncurses=6.5=he02047a_1
-  - nettle=3.9.1=h7ab15ed_0
-  - networkx=3.4.2=pyh267e887_2
-  - numpy=2.2.0=py310h5851e9f_0
-  - openh264=2.3.1=hcb278e6_2
-  - openjpeg=2.5.3=h5fbd93e_0
-  - openssl=3.4.0=hb9d3cd8_0
-  - p11-kit=0.24.1=hc5aa10d_0
-  - pip=24.3.1=pyh8b19718_0
-  - pthread-stubs=0.4=hb9d3cd8_1002
-  - pycparser=2.22=pyh29332c3_1
-  - pysocks=1.7.1=pyha55dd90_7
-  - python=3.10.16=he725a3c_1_cpython
-  - python_abi=3.10=5_cp310
-  - pytorch=2.5.1=py3.10_cuda12.4_cudnn9.1.0_0
-  - pytorch-cuda=12.4=hc786d27_7
-  - pytorch-mutex=1.0=cuda
-  - pyyaml=6.0.2=py310ha75aee5_1
-  - readline=8.2=h8228510_1
-  - requests=2.32.3=pyhd8ed1ab_1
-  - setuptools=75.6.0=pyhff2d567_1
-  - svt-av1=1.4.1=hcb278e6_0
-  - tbb=2021.13.0=hceb3a55_1
-  - tk=8.6.13=noxft_h4845f30_101
-  - torchaudio=2.5.1=py310_cu124
-  - torchtriton=3.1.0=py310
-  - torchvision=0.20.1=py310_cu124
-  - typing_extensions=4.12.2=pyha770c72_1
-  - urllib3=2.2.3=pyhd8ed1ab_1
-  - wayland=1.23.1=h3e06ad9_0
-  - wayland-protocols=1.37=hd8ed1ab_0
-  - wheel=0.45.1=pyhd8ed1ab_1
-  - x264=1!164.3095=h166bdaf_2
-  - x265=3.5=h924138e_3
-  - xorg-libx11=1.8.10=h4f16b4b_1
-  - xorg-libxau=1.0.11=hb9d3cd8_1
-  - xorg-libxdmcp=1.1.5=hb9d3cd8_0
-  - xorg-libxext=1.3.6=hb9d3cd8_0
-  - xorg-libxfixes=6.0.1=hb9d3cd8_0
-  - yaml=0.2.5=h7f98852_2
-  - zstandard=0.23.0=py310ha39cb0e_1
-  - zstd=1.5.6=ha6fb4c9_0
-  - pip:
-      - accelerate==1.2.1
-      - aiofiles==23.2.1
-      - annotated-types==0.7.0
-      - anyio==4.7.0
-      - click==8.1.7
-      - contourpy==1.3.1
-      - cycler==0.12.1
-      - decorator==4.4.2
-      - decord==0.6.0
-      - distro==1.9.0
-      - einops==0.8.0
-      - exceptiongroup==1.2.2
-      - fastapi==0.115.6
-      - ffmpy==0.4.0
-      - fonttools==4.57.0
-      - fsspec==2024.10.0
-      - gradio==5.9.0
-      - gradio-client==1.5.2
-      - h11==0.14.0
-      - httpcore==1.0.7
-      - httpx==0.28.1
-      - huggingface-hub==0.26.5
-      - imageio==2.37.0
-      - imageio-ffmpeg==0.6.0
-      - jiter==0.9.0
-      - joblib==1.4.2
-      - kiwisolver==1.4.8
-      - markdown-it-py==3.0.0
-      - markupsafe==2.1.5
-      - matplotlib==3.10.1
-      - mdurl==0.1.2
-      - moviepy==1.0.3
-      - openai==1.70.0
-      - opencv-python==4.10.0.84
-      - orjson==3.10.12
-      - packaging==24.2
-      - pandas==2.2.3
-      - pillow==10.4.0
-      - proglog==0.1.10
-      - psutil==6.1.1
-      - pycarl==2.3.0
-      - pydantic==2.10.3
-      - pydantic-core==2.27.1
-      - pydub==0.25.1
-      - pygments==2.18.0
-      - pyparsing==3.2.3
-      - python-dateutil==2.9.0.post0
-      - python-dotenv==1.0.1
-      - python-multipart==0.0.19
-      - pytz==2024.2
-      - regex==2024.11.6
-      - rich==13.9.4
-      - ruff==0.8.3
-      - safehttpx==0.1.6
-      - safetensors==0.4.5
-      - semantic-version==2.10.0
-      - sentencepiece==0.2.0
-      - shellingham==1.5.4
-      - six==1.17.0
-      - sniffio==1.3.1
-      - starlette==0.41.3
-      - stormpy==1.9.0
-      - sympy==1.13.1
-      - timm==1.0.13
-      - tokenizers==0.21.0
-      - tomlkit==0.13.2
-      - tqdm==4.67.1
-      - transformers==4.47.0
-      - typer==0.15.1
-      - tzdata==2024.2
-      - uvicorn==0.32.1
-      - websockets==14.1
-prefix: /home/ss99569/mambaforge/envs/neusv-public-1

launch_space.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # Start vLLM server in background
-./vllm_serve.sh > /dev/null 2>&1 &
+./vllm_serve.sh
 
 # Wait briefly to ensure vLLM is up before Gradio tries to connect
 sleep 60

requirements.txt

@@ -6,7 +6,7 @@ torchaudio==2.4.0
 
 # Other packages
 --index-url https://pypi.org/simple
-gradio==5.9.0
+gradio==5.25.0
 transformers==4.47.0
 opencv-python==4.10.0.84
 decord==0.6.0

vllm_serve.sh

@@ -11,4 +11,5 @@ vllm serve $MODEL \
     --trust-remote-code \
     --limit-mm-per-prompt image=4 \
     --max-model-len 8192 \
-    --gpu-memory-utilization 0.97
+    --gpu-memory-utilization 0.97 \
+    --disable-log-requests