whn09 c4c50f1ea5 neuron: shared expert sliced over ranks, summed in the MoE all-reduce (DEEPINFER_NEURON_SHARED_SLICE=1) ... 18 of 64 ranks compute a 128-column slice of the 2304-wide shared expert (the rest add zeros, same graph); the partial joins the routed experts' sum before the existing all-reduce. Decode step 591 -> 581 ms. Summation order changes, so greedy outputs differ from before (coherent; tokens/step 2.70/3.10/3.34, TPOT p50 184 ms). Tiny golden 9/9. Also DEEPINFER_NEURON_HOST_TIMING (host time per region call). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-27 01:31:41 +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: shared expert sliced over ranks, summed in the MoE all-reduce (DEEPINFER_NEURON_SHARED_SLICE=1)	2026-10-27 01:31:41 +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