microsoft / microsoft/fara

Installation failure on Windows while installing vllm-0.10.0

Open
#21 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.2k
Forks
603
PR merge metrics
No merged PRs in 30d

Description

Hey!

Attempting to install vllm==0.10.0 on Windows using Miniconda3 + Python 3.12 results in a wheel build failure. The error occurs during the creation of quantization config JSON files, where the build system attempts to createpaths containing commas and brackets. Windows fails to create these paths, causing the install to abort.

This blocks local development for serving the model.

error: could not create 'build\bdist.win-amd64\wheel\.\vllm\model_executor\layers\quantization\utils\configs\N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json': No such file or directory

ERROR: Failed building wheel for vllm
Failed to build vllm
ERROR: Failed to build installable wheels for some pyproject.toml based projects (vllm)
Building wheels for collected packages: vllm
  Building wheel for vllm (pyproject.toml) ... error
  error: subprocess-exited-with-error

  × Building wheel for vllm (pyproject.toml) did not run successfully.
  │ exit code: 1
  ╰─> [1988 lines of output]
      C:\Users\ital-\AppData\Local\Temp\pip-build-env-kmwzxubg\overlay\Lib\site-packages\torch\_subclasses\functional_tensor.py:276: UserWarning: Failed to initialize NumPy: No module named 'numpy' (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\torch\csrc\utils\tensor_numpy.cpp:81.)
        cpu = _conversion_method_template(device=torch.device("cpu"))
      vLLM only supports Linux platform (including WSL) and MacOS.Building on win32, so vLLM may not be able to run correctly
      C:\Users\ital-\AppData\Local\Temp\pip-build-env-kmwzxubg\overlay\Lib\site-packages\setuptools_scm\_integration\version_inference.py:51: UserWarning: version of None already set
        warnings.warn(self.message)

It looks like vLLM is only supported by WSL when running on Windows?

This happens consistently when running:

python -m pip install -r requirements.txt

OS | Windows 11
Python | 3.12
vLLM Version | 0.10.0

Any assistance would be greatly appreciated

Thanks!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with requirements.txt and reproduce the python -m pip install -r requirements.txt failure on Windows 11 with Python 3.12. Inspect how the quantization config JSON paths are created, and verify the documented platform support; done means the Windows installation either completes successfully or the unsupported configuration is clearly established.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
build-system, operating-systems
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.