All posts on technology, daily life, and thoughts.
If the GPU processes only one sequence at a time, it sits idle while that sequence finishes prefill and moves on to decode. Continuous batching is the approach of feeding…
StepAudio 3 Gen: Unifying Speech, Song, Music, and Sound Effects with a Single Discrete Autoregressive (RVQ) Model TL;DR StepAudio 3 Gen, released by StepFun, is a fully…
Is "Lossless" Speculative Decoding Really Lossless? — The Numerical-Precision Trap Exposed by Reproducing Orthrus TL;DR — Orthrus attaches a diffusion view to a frozen AR…
ZGCM-1: How a 7B Dense Model Trades Blows with 235B Frontiers — A Fully Open, Ultra-Efficient Foundation Model Design Report TL;DR — With a single 7.39B dense model,…
Programmable World Model — Embedding "Executable State" into Generative Worlds One-Line Summary (TL;DR) Video world models are producing increasingly realistic…
SAS: A Simple Attention Sparsification That Learns Context Ranking Directly Without Distillation TL;DR — In post-training attention sparsification, inject the continuous…