vLLM installation instructions outdated - PyTorch nightly build no longer available #2330

Problem

The current installation instructions in articles/gpt-oss/run-vllm.md fail because the PyTorch nightly build torch==2.9.0.dev20250804+cu128 required by vllm==0.10.1+gptoss is no longer available.

Users encounter this error:

× No solution found when resolving dependencies:  ╰─▶ Because there is no version of torch==2.9.0.dev20250804+cu128 and vllm==0.10.1+gptoss depends on torch==2.9.0.dev20250804+cu128, we can conclude that vllm==0.10.1+gptoss cannot be used.

Working Solution

The following installation steps work:

uv venv --python 3.12 --seed
source . venv/bin/activate

# Install PyTorch 2.9.0 for CUDA 12.8
uv pip install https://download.pytorch.org/whl/cu128/torch-2.9.0%2Bcu128-cp312-cp312-manylinux_2_28_x86_64.whl

# Install latest vLLM from gpt-oss wheels
uv pip install --pre vllm \
  --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
  --index-strategy unsafe-best-match

Suggested Fix

Update the Quick Setup section in articles/gpt-oss/run-vllm.md to use these working instructions instead of the current ones.

Additional Context

• Tested on Ubuntu with CUDA 12.8, Python 3.12
• Successfully runs vllm serve openai/gpt-oss-20b
• Community members on Hugging Face have reported the same issue