SIGN IN SIGN UP

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 122 Python

[Perf] Add H100 fused MoE config (#25398)

Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Z
ZiTian Zhao committed
c981f0ea787c57ad9745964f8777df760cfb1792
Parent: 6367bde
Committed by GitHub <noreply@github.com> on 10/18/2025, 2:21:27 AM