Factual package intelligence from PyPI

turboquant-vllm 1.5.0 package intelligence

TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090

pip install turboquant-vllm

Current version
1.5.0
Python requirement
>=3.12
License
Apache-2.0
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
152.8 KiB
Release history
11 releases with files
Median release cadence
1 days

turboquant-vllm dependencies

PyPI declares 16 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. torch >=2.6
  2. torchvision >=0.21
  3. transformers >=4.57
  4. molmo-utils >=0.0.1
  5. scipy >=1.10
  6. accelerate >=0.25
  7. einops >=0.8
  8. vllm >=0.19

Compatibility and release files

turboquant-vllm publishes 1 wheel and 1 source archive for version 1.5.0. Wheel platform tags: any.

Declared Python classifiers: 3.12, 3.13.

Release activity and sources

PyPI lists 11 releases with files. The first dated release is ; 11 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .