#turboquant

The latest AI and developer news about #turboquant, with the original source and a short summary.

Google TurboQuant-based Rust Vector Index 'Turbovec' Released, Improving Compression and Speed Over FAISS

Turbovec, a Rust vector index applying Google Research's TurboQuant, offers faster search and higher compression rates than FAISS.

·1·2026.08.19 21:00

Turbovec – A Rust-based Vector Search Engine for Google TurboQuant

Turbovec, a Rust-based vector search engine leveraging Google's TurboQuant algorithm, has been released, offering faster and more memory-efficient performance than FAISS.

·1·2026.08.19 03:00

Core Technologies for LLM Inference Optimization: Quantization, KV Cache, and Inference Chips

Quantization, KV cache compression, and inference chips reduce the cost and latency of agentic AI.

·2026.08.06 14:00

TurboQuant Accuracy and Performance Evaluation

vLLM concluded that FP8 KV-cache is the default choice, while TurboQuant's higher-bit options offer little real benefit.

·1·2026.05.15 05:00

vLLM fixes Qwen TurboQuant error

vLLM has resolved the unimplemented TurboQuant error affecting Qwen 3.5+ models caused by an issue with Mamba layers.

·1·2026.05.05 09:00

Valkyr with TurboQuant applied

A TurboQuant inference path was added to Runtime Valkyr, achieving 120 tok/s on Gemma with an RTX 3090.

·2026.04.30 04:00

TurboQuant fixes Qwen3.6

TurboQuant fixed a speculative decoding bug in its Qwen3.6 fork.

·1·2026.04.22 08:00