tzhouamandClaude Fable 5.1 3085f50160 [Edge][CPU] Compile the per-sub-step lm head + top-k Gumbel sampling + embedding + projection into one graph ...

Noise is drawn eagerly with the request generators (same RNG consumption as the
eager loop) and passed in, so the compiled post-step is generator-free and
shape-static; used on the fp32/torchao CPU path outside stored (top-p) mode.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-10 03:12:40 +08:00

..

__init__.py

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00

test_code_predictor_incremental.py

[Edge][CPU] Compile the per-sub-step lm head + top-k Gumbel sampling + embedding + projection into one graph

2026-09-10 03:12:40 +08:00

test_fused_adaptive_group_norm_silu.py

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00

test_fused_group_norm_silu.py

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00