日本語のみで絞り込む
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality ...
Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), ...
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration - 0xSero/turboquant.
TurboQuant is a compression method that achieves a high reduction in model size with zero accuracy loss, making it ideal for supporting both key-value (KV) ...
turbovec is an in-process vector index for Python and Rust. It stores each vector at 2 or 4 bits per dimension using Google Research's TurboQuant and searches ...
A from-scratch PyTorch implementation of TurboQuant (ICLR 2026), Google's vector quantization algorithm for compressing LLM key-value caches.
Most of this repo is TurboQuant in WASM: a Zig → WASM build with relaxed SIMD that encodes / decodes / scores vectors on the CPU. That's what the turboquant- ...
2026/3/25 -TurboQuant complements lower bit-width quantization by removing biases and improving accuracy with mathematically grounded techniques.
Hi everyone, We've spent the last 12 hours building a production-ready implementation of Google DeepMind's TurboQuant (arXiv:2504.19874).
2026/3/28 -TurboQuant is a novel online vector quantization method from the Google ICLR 2026 paper "TurboQuant: Online Vector Quantization with Near ...