wheelgap tracker

litellm wheel coverage

pip install litellm on Python 3.14: wheels for the whole tree on 5 of the 6 platforms checked; on Windows ARM64 it builds fastuuid and 2 more from source.

From the wheelgap 0.9.0 scan of 2026-11-16.

litellm 1.109.1

#295 by downloads · PyPI

Campaigns: On the to-do list of Windows on ARM wheels for the top 500.

Platform3.133.143.14t3.153.15t
Linux x86_64wheelwheelfrom sourcebuilds in 10 min, but importing it turns the GIL back onwheelfrom source
Linux ARM64wheelwheelfrom sourcewheelfrom source
Alpine x86_64wheelwheelfrom sourcewheelfrom source
Alpine ARM64wheelwheelfrom sourcewheelfrom source
macOS Apple siliconwheelwheelfrom sourcewheelfrom source
macOS Intelwheelwheelfrom sourcewheelfrom source
Windows x86_64wheelwheelfrom sourcewheelfrom source
Windows ARM64from sourcefrom sourcebuilds from source in 16 min and importsfrom sourcebuilds in 15 min, but importing it turns the GIL back onfrom sourcefrom source
Pyodide (browser)can't installcan't installn/an/an/a

Why? uvx wheelgap litellm==1.109.1 -p 3.15 -t all --explain

Install coverage with dependencies

Wheelgap checks the scanned release and its dependencies without extras. A target is marked “Not checked” if wheelgap could not resolve the full dependency tree or verify its packages.

TargetInstall result
3.14 linux-x86_64Wheels for the whole tree
3.14 linux-aarch64Wheels for the whole tree
3.14 musl-aarch64Wheels for the whole tree
3.14 macos-arm64Wheels for the whole tree
3.14 macos-x86_64Wheels for the whole tree
3.14 win-arm64Builds from source
  • fastuuid==0.14.0 builds from source via litellm → fastuuid
  • litellm==1.109.1 builds from source
  • tiktoken==0.14.0 builds from source via litellm → tiktoken
3.14t linux-x86_64Builds from source
  • fastuuid==0.14.0 builds from source via litellm → fastuuid
  • litellm==1.109.1 builds from source
3.14t win-arm64Builds from source
  • fastuuid==0.14.0 builds from source via litellm → fastuuid
  • litellm==1.109.1 builds from source
  • rpds-py==2026.9.1 builds from source via litellm → jsonschema → rpds-py
  • tiktoken==0.14.0 builds from source via litellm → tiktoken
  • tokenizers==0.23.3 builds from source via litellm → tokenizers

Build lab

A dated observation on GitHub's runners, not a promise about your machine: runners come with compilers and many system libraries preinstalled, so a build that works there can still need setup on your machine.

TargetFrom sourceDetails
3.14 win-arm64works builds from source in 16 min and importswindows-11-arm, Python 3.14.10, 2026-11-15 · run
3.14t linux-x86_64GIL back on builds in 10 min, but importing it turns the GIL back onubuntu-24.04, Python 3.14.10t, 2026-11-15 · run
3.14t win-arm64GIL back on builds in 15 min, but importing it turns the GIL back onwindows-11-arm, Python 3.14.10t, 2026-11-15 · run

Notes

No notes for litellm yet.

Know a workaround, an alternative package, a conda-forge build or an upstream issue for litellm? Add a note (a pull request on GitHub; the format is in notes/README.md).

Badge for your README

[![wheels](https://img.shields.io/endpoint?url=https://wheelgap.github.io/tracker/badge/litellm.json)](https://wheelgap.github.io/tracker/#package=litellm)
[![wheels with dependencies](https://img.shields.io/endpoint?url=https://wheelgap.github.io/tracker/badge/litellm-tree.json)](https://wheelgap.github.io/tracker/p/litellm/)

Package JSON

All 5,000 packages