# TheTom/turboquant_plus

Repository: https://github.com/TheTom/turboquant_plus
Canonical: https://ross.abutalabs.com/products/turboquant_plus
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-20T20:08:52+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 35, longevity 11
- inputs: {"age_days": 162, "days_push": 44, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7006, forks 925 (observed 2026-08-28T04:09:53.194458+00:00)

## What it is
TurboQuant+ is a Python reference implementation of the TurboQuant KV cache compression method (ICLR 2026), using PolarQuant codebooks and Walsh-Hadamard rotation to compress transformer KV caches 3.8-6.4x. It serves as the research home with benchmarks and validation results, with stable pieces upstreamed into engines like vLLM and llama.cpp.

## Use cases
- compress kv cache for long-context llm inference
- run 100b model on limited memory via cache quantization
- benchmark kv cache quantization methods
- reduce gpu memory usage for transformer inference
- research extreme kv cache compression
- speed up llm decode at long context

## When to choose
- you need the full PolarQuant codec or asymmetric K/V policies not yet upstreamed
- you want the reference implementation and benchmark data for research
- you want to run very large models at long context on consumer hardware like a MacBook

## When to avoid
- you just want production KV compression in a datacenter engine - use the merged vLLM flag instead
- you need a turnkey inference server - this is a research library, not an inference engine
- you need non-transformer model compression

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, benchmarking, gpu-computing
- domain: large-language-models, deep-learning, machine-learning, performance
- platform: python, windows, cross-platform
- tags: kv-cache-compression, quantization, polarquant, walsh-hadamard-transform, inference-optimization, research-code, memory-optimization, gpu, macos, linux

## Member repositories
- TheTom/turboquant_plus (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:53.194458+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:40:44.702760+00:00, confidence not recorded.
  - readme: https://github.com/TheTom/turboquant_plus (fetched 2026-08-28T04:09:53.194458+00:00, sha cfd46ee1f2f7)
- Data as of 2026-08-30T08:39:29.467469+00:00.