whn09 f67fab6bdd Neuron MoE: two-level all-reduce (device, then across devices) (#27) ... Microbenchmark at 64 ranks, [1, 5120] fp32 in a compiled graph: world all-reduce 3.37 ms, 8 consecutive ranks 0.41 ms, 4-core device group then a 16-device group (one core each) 2.01 ms; a strided 8-device group is rejected by the runtime. The replicated-token MoE all-reduce (one a layer) now takes the two-level form (DEEPINFER_NEURON_HIER_ALLREDUCE=0 restores one world all-reduce). Host tiny cp=8 matches golden. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-24 11:05:25 +08:00
..
mtp	initial commit	2026-10-20 12:09:42 +08:00
v4_modules	Neuron MoE: two-level all-reduce (device, then across devices) (#27)	2026-10-24 11:05:25 +08:00
vision_encoder	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
decoder_layer.py	Neuron: optional whole-layer region graph (DEEPINFER_NEURON_REGION_LAYER)	2026-10-24 09:51:01 +08:00
deepseek_vl.py	Neuron: full DeepSeek-V4.1-Flash load + decode region graphs at EP=64 (issues #21, #25)	2026-10-23 01:39:22 +08:00
deepseek.py	Neuron: full DeepSeek-V4.1-Flash load + decode region graphs at EP=64 (issues #21, #25)	2026-10-23 01:39:22 +08:00