Factual package intelligence from PyPI

squish-ai 9.34.14 package intelligence

Local LLM inference server for Apple Silicon. Block-level paged KV cache for long-context workloads. 5.4× faster end-to-end on 4K-token prompts vs Ollama, less RAM, INT3 support for Qwen3. OpenAI-comp

pip install squish-ai

Current version
9.34.14
Python requirement
<3.15,>=3.11
License
BUSL-1.1
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
3.9 MiB
Release history
25 releases with files
Median release cadence
1 days

squish-ai dependencies

PyPI declares 35 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. mlx >=0.18 when sys_platform == "darwin" and platform_machine == "arm64"
  2. mlx-lm >=0.19 when sys_platform == "darwin" and platform_machine == "arm64"
  3. numpy >=1.26
  4. safetensors >=0.4
  5. fastapi >=0.111
  6. uvicorn >=0.29
  7. sse-starlette >=1.8
  8. huggingface-hub >=0.23
  9. transformers <5.13.0,>=4.40
  10. zstandard >=0.22
  11. rich >=13.0
  12. orjson >=3.11.9

The compact report shows 12 of 35 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

squish-ai publishes 1 wheel and 1 source archive for version 9.34.14. Wheel platform tags: any.

Declared Python classifiers: 3.11, 3.12, 3.13, 3.14.

Security snapshot for squish-ai 9.34.14

An OSV query completed on and found 0 known vulnerabilities affecting this version. 0 advisories are classified as critical. 0 advisories appear in the CISA Known Exploited Vulnerabilities catalog.

Release activity and sources

PyPI lists 25 releases with files. The first dated release is ; 25 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .