SIGN IN SIGN UP

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

0 0 122 Python

[GPTOSS][DP/EP][Marlin] Enable GPTOSS Batched DP/EP using Marlin kernels (#25997)

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
V
Varun Sundar Rabindranath committed
fb0571b077e749d041c1d9802dda5ceb42c9e8b1
Parent: 2ed8b6b
Committed by GitHub <noreply@github.com> on 10/16/2025, 7:53:11 PM