vllmellm 1a19e9cd87 [Bugfix][ROCm]Fix Qwen3-Next-80B-A3B-Thinking inference and optimize non-standard block size (544) support under rocm_atten (#31380) ...

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

2026-01-09 19:28:02 +08:00

22 KiB

Raw Blame History

View Raw