whn09 976f9fe4d2 Neuron DSpark: 6-row steps keep only coarse region splits (8 graphs a layer instead of 12)
neuronx-cc segfaults (LegalizeSundaAccess) when the 6-row projections are merged
with the indexer, so that boundary stays; the other fine splits are prompt-only.
bench28 (512 in, 128 out, TP=64, nextn=5): TPOT 277.4 -> 272.6 ms, 3.85 tokens
a step.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 00:31:45 +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 DSpark (#15): greedy verification and MTP ops, CP followers run the drafts 2026-10-24 11:31:59 +08:00
models Neuron DSpark: 6-row steps keep only coarse region splits (8 graphs a layer instead of 12) 2026-10-25 00:31:45 +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