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.

27
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

—

Language

Python

License

MIT

Category

kv-cache-optimization

Last pushed

Mar 25, 2026

Commits (30d)

0

GitHub
Kv Cache Optimization · 7 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/codepawl/turboquant-torch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Compare

turboquant-torch and turboquant

Higher-rated alternatives

LMCache/LMCache

Supercharge Your LLM with the Fastest KV Cache Layer

92

Zefan-Cai/KVCache-Factory

Unified KV Cache Compression Methods for Auto-Regressive Models

47

dataflowr/llm_efficiency

KV Cache & LoRA for minGPT

41

itsnamgyu/block-transformer

Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)

38

OnlyTerp/turboquant

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache...

35

Explore Transformer Models

All categories Trending Transformer directory Insights