whn09 c826e81b71 neuron: mHC collapse through torch by default (DEEPINFER_NEURON_HC_TORCH=collapse); fix Neuron bind_cpu core index ... collapse in torch is bit-exact with the hc_collapse kernel and a faster graph (512 rows: 0.15 vs 1.73 ms standalone). post_torch (the kernel's operation order) is bit-equal standalone but rounds differently fused in the layer graph, so it is opt-in. Tiny golden 9/9 with collapse. bind_cpu receives the physical core id; _neuron_bind_cpus indexed CUDA_VISIBLE_DEVICES with it again (broke runs on cores other than 0..n). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-27 09:18:56 +08:00
..
mtp	neuron: drafter forward as one region, compiled dflash metadata fill; verification + drafts regions on by default	2026-10-27 00:14:32 +08:00
v4_modules	neuron: mHC collapse through torch by default (DEEPINFER_NEURON_HC_TORCH=collapse); fix Neuron bind_cpu core index	2026-10-27 09:18:56 +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 DSpark: 6-row steps keep only coarse region splits (8 graphs a layer instead of 12)	2026-10-25 00:31:45 +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