turboquant and turboquant-torch

turboquant
35
Emerging
turboquant-torch
27
Experimental
Maintenance 13/25
Adoption 7/25
Maturity 9/25
Community 6/25
Maintenance 13/25
Adoption 5/25
Maturity 9/25
Community 0/25
Stars: 36
Forks: 2
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 9
Forks:
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About turboquant

OnlyTerp/turboquant

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

About turboquant-torch

codepawl/turboquant-torch

Unofficial PyTorch implementation of TurboQuant (Google Research, ICLR 2026). Near-optimal vector quantization for KV cache compression and vector search. 3-bit with zero accuracy loss.

Scores updated daily from GitHub, PyPI, and npm data. How scores work