LMSYS Megakernel Boosts Muse Spark Decoding to 1,109 tok/s

LMSYS built a from-scratch CUDA C++/PTX megakernel for Muse Spark Open that reaches 1,109 tokens/s on 8×GB300, 2.1× the baseline, while cutting kernel launches from 1,450 to 97.

2026-11-12 ~ 2026-11-12 · 2 related posts

• LMSYS megakernel pushes decoding to 1,109 tok/s on 8× GB300, launches cut 1450→97 — ying11231 · 2026-11-12
• SGLang Megakernel Pushes Muse Spark to 1,109 tok/s, 2.1x Over Baseline — hsu_byron · 2026-11-12