5 Commits

Author	SHA1	Message	Date
Zijie Tian	c51a640a29	🐛 fix: remove torch.compile from add_rms_forward to avoid recompilation ... The add_rms_forward method processes two input tensors (x and residual), which causes torch.compile recompilation issues. Keep @torch.compile only on rms_forward which processes a single input. This prevents unnecessary recompilation overhead during inference. Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-14 07:02:02 +08:00
Zijie Tian	babfa17354	[refactor] Translate into english, void Chinese due to claude.	2025-12-11 00:30:24 +08:00
GeeeekExplorer	df99418f7d	simplify	2025-08-31 20:02:51 +08:00
GeeeekExplorer	38baf0bbe4	remove assert shape	2025-06-27 23:00:30 +08:00
GeeeekExplorer	a5a4909e6a	init commit	2025-06-10 00:27:01 +08:00