whn09 d27e8951db neuron: the grouped wv projection takes the bf16 context through the NKI qdq kernel instead of an in-graph fp8 encode (TTFT 1009 -> 942 ms, step 437 -> 414 ms, tokens identical) ... Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-28 14:32:47 +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: single-request prompt chunks attend densely over their own SWA ring and compressed blocks, masks from positions (DEEPINFER_NEURON_PREFILL_DENSE, check mode DEEPINFER_NEURON_PREFILL_DENSE_CHECK)	2026-10-28 09:09:34 +08:00
models	neuron: the grouped wv projection takes the bf16 context through the NKI qdq kernel instead of an in-graph fp8 encode (TTFT 1009 -> 942 ms, step 437 -> 414 ms, tokens identical)	2026-10-28 14:32:47 +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: norms feeding only NKI kernels skip their dead fp8 copy (TTFT 1387 -> 1229 ms, step 457 -> 450 ms, tokens identical); capacity MoE wired into the layer region graph with its overflow flag riding the MoE all-reduce (still off: per-layer host sync makes prefill slower, 1823 ms)	2026-10-28 05:29:40 +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