PyPI page
Home page
Author:
pbertsch
Summary:
TurboQuant KV cache compression for local LLM inference
Latest version:
0.6.0
Required dependencies:
numpy
Optional dependencies:
cma
|
mlx
|
mlx-lm
|
pytest
|
pytest-cov
|
ruff
|
scipy
|
torch
|
transformers
|
triton
Downloads last day:
3
Downloads last week:
73
Downloads last month:
453