Tag
This paper introduces inner product aware quantization methods that preserve inner products with unseen vectors, developing fast and adaptive algorithms with provable guarantees, achieving 2-10x speedup over prior ASQ methods.
Shard is a drop-in HuggingFace Cache that achieves 10x KV cache compression for Llama-3.1-8B by using PCA plus int4 quantization on K and Hadamard rotation plus vector quantization on V, without accuracy loss on benchmarks.
This paper introduces SDFlow, a similarity-driven flow matching framework for time series generation that addresses exposure bias in autoregressive models. It achieves state-of-the-art performance and inference speedups by operating in the frozen VQ latent space with low-rank manifold decomposition.
IndexTTS is an enhanced text-to-speech system that combines XTTS and Tortoise models with hybrid character-pinyin modeling and optimized vector quantization, achieving improved naturalness, controllable pronunciation, and faster inference than existing open-source TTS systems.