whn09 fb9dea85cb Neuron sampler: skip the top-p/top-k bisection when no row filters (#27) ... The bisection is 32 rounds over the vocabulary: ~0.5 s a decode step at 129280 even compiled, and the default parameters (top_p 1, top_k -1) filter nothing. Such batches take the plain temperature log-softmax: 529.6 -> 1.3 ms on one core, same tokens, logprobs within 1e-9. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-23 12:05:16 +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 sampler: skip the top-p/top-k bisection when no row filters (#27)	2026-10-23 12:05:16 +08:00
models	Neuron: skip the vacuous candidate-block filter; mask padding rows in static MoE (#26)	2026-10-23 05:25:28 +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: full DeepSeek-V4.1-Flash load + decode region graphs at EP=64 (issues #21, #25)	2026-10-23 01:39:22 +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