whn09 ad6b47a141 Neuron: head-sharded attention over the CP group (TP decode) (#28) ... With a CP group running one replicated batch (DEEPINFER_NEURON_TP_ATTN, on when cp > 1), each rank keeps its heads' rows of q_b, its groups' slice of wv (or its heads' columns of one group), the matching out_proj columns and its attention-sink entries; _wv_and_o_proj all-reduces the partial outputs over the group (exact: wv and out_proj are linear in the heads; asserts no clamp). Q-a / KV / indexer / compressor stay replicated. Host tiny (8 heads, 2 groups): cp=2 (1 group a rank), cp=4 (2 heads of a group), cp=8 (1 head) all give the golden tokens up to near ties. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-23 22:53:32 +08:00
..
mtp	initial commit	2026-10-20 12:09:42 +08:00
v4_modules	Neuron: head-sharded attention over the CP group (TP decode) (#28)	2026-10-23 22:53:32 +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: count MoE capacity overflows under DEEPINFER_NEURON_REGION_TIMING	2026-10-23 16:23:28 +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