whn09 6c653df08c neuron: drafter forward as one region, compiled dflash metadata fill; verification + drafts regions on by default ... vllm-sonnet 512 (Trn2-Hy4): decode step 660 -> 591 ms, TPOT 221.7 -> 206.5 ms (p50), TTFT 4.02 -> 3.93 s, tokens/step identical (3.02/2.82/2.65). Tiny golden 9/9. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-27 00:14:32 +08:00
..
tilelang_ops	neuron: drafter forward as one region, compiled dflash metadata fill; verification + drafts regions on by default	2026-10-27 00:14:32 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
attention_backend.py	initial commit	2026-10-20 12:09:42 +08:00
layernorm.py	initial commit	2026-10-20 12:09:42 +08:00
linear.py	Neuron: per-layer region graphs + vllm-neuron#71 NKI kernels (issues #10, #11, #13, #25)	2026-10-22 17:36:54 +08:00
mtp_info_pool.py	initial commit	2026-10-20 12:09:42 +08:00
rotary_embedding.py	initial commit	2026-10-20 12:09:42 +08:00
sampler_utils.py	initial commit	2026-10-20 12:09:42 +08:00
sampler.py	neuron: compiled decode verification behind DEEPINFER_NEURON_COMPILE_VERIFY (default off)	2026-10-26 21:33:34 +08:00
vocab_parallel_embedding.py	Neuron: eager embedding/gather without dtype casts or host scalar operands	2026-10-25 06:55:43 +08:00