Morph MORPH
SIGN IN SIGN UP
tejas / vllm

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

0 0 122 Python

[BugFix] GPT-OSS Attention DP + MoE TP weight loading issue (#24032)

Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
P
Po-Han Huang (NVIDIA) committed
aef368aa08572505b820db01da82e2fbb3d43a72
Parent: 5f6cbf6
Committed by GitHub <noreply@github.com> on 10/21/2025, 4:03:47 AM