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
..
eplb	initial commit	2026-10-20 12:09:42 +08:00
input_metadata	initial commit	2026-10-20 12:09:42 +08:00
layers	neuron: drafter forward as one region, compiled dflash metadata fill; verification + drafts regions on by default	2026-10-27 00:14:32 +08:00
models	neuron: drafter forward as one region, compiled dflash metadata fill; verification + drafts regions on by default	2026-10-27 00:14:32 +08:00
parallel_utils	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
layer_utils.py	initial commit	2026-10-20 12:09:42 +08:00
model_loader.py	Neuron: CP group as a replicated-decode group; MoE all-reduce mode (#28)	2026-10-23 22:46:04 +08:00
model_metadata_utils.py	Neuron: prompt chunks through the decode region graphs (issue #26)	2026-10-23 03:19:56 +08:00
model_output.py	initial commit	2026-10-20 12:09:42 +08:00
sampling_inputs.py	initial commit	2026-10-20 12:09:42 +08:00
utils.py	Neuron: static decode graphs, static-shape MoE, trn2 e4m3 fp8 (issues #9, #12, #24)	2026-10-22 11:59:37 +08:00