SIGN IN SIGN UP

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

0 0 122 Python

[ROCM] MoE fp4 CK kernel (#26545)

Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
A
Aleksandr Malyshev committed
0925b28a8e92855131a1c1308a16ec14a9c94ceb
Parent: 99722d5
Committed by GitHub <noreply@github.com> on 10/17/2025, 6:06:33 PM