Repo

turboquant-pro

@ahb-sjsuby Andrew Bond · Computer Engineering Department at San José State University

0

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.

Built withPythoncompressionembeddingskv-cachellmpytorchquantization

See what other members are building and what each project is looking for.