ahb-sjsu/turboquant-pro

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

2 best points · 0 comments · 1 Hacker News post · 27 GitHub stars · View on GitHub

Hacker News discussions

• TurboQuant Pro – 27-41x embedding compression via PCA-Matryoshka (2 points, 0 comments, by ahb-sjsu, 2026-04-10)