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

..

activation.py

fix

2025-06-15 13:28:29 +08:00

attention.py

[claudesquad] update from 'lw-offload-2' on 08 Jan 26 20:53 CST

2026-01-08 20:53:08 +08:00

embed_head.py

simplify

2025-08-31 20:02:51 +08:00

layernorm.py

🐛 fix: remove torch.compile from add_rms_forward to avoid recompilation

2026-01-14 07:02:02 +08:00

linear.py

simplify

2025-08-31 20:02:51 +08:00

rotary_embedding.py

[claudesquad] update from 'add-llama-1' on 10 Jan 26 21:03 CST

2026-01-10 21:03:45 +08:00

sampler.py

[feat] Added bench_offload.py and GreedySampler.

2025-12-12 00:24:08 +08:00