Kosinkadink fd79f22bdf Backport Hunyuan 3D 2.1 attention batch-size fixes from #13699 ... CrossAttention.kv.view and Attention.qkv_combined.view both hardcoded batch=1 in the reshape, crashing or silently mis-shaping whenever the actual batch dimension was greater than 1. These were fixed on master in #13699 as part of the same patch that gated the chunk(2) swap, but worksplit-multigpu only picked up the chunk(2) gate. Bring the two view() fixes over so we have parity with master. Amp-Thread-ID: https://ampcode.com/threads/T-019e4a00-fe3d-76bd-a2f2-a8c8c4040082 Co-authored-by: Amp <amp@ampcode.com>		2026-05-21 12:17:24 -07:00
..
hunyuandit.py	Backport Hunyuan 3D 2.1 attention batch-size fixes from #13699	2026-05-21 12:17:24 -07:00