whn09 ee9e3aaed9 Neuron DSpark: draft sampling as one region graph for greedy rows; token embedding on device by default ... - DFlash._greedy_drafts: post norm, LM head, Markov bias, confidence head and the argmax of the 5 draft steps as one region graph when every row is greedy with no top-p/top-k filter. - DEEPINFER_NEURON_HOST_EMBED defaults off: in torch-neuronx every host<->device copy drains the stream, and the host lookup (D2H ids, H2D rows) left the cores idle for 50-100 ms gaps between the draft graphs (runtime trace bench36). - Eager device embedding lookups are one F.embedding with a validity mask (no host scalar operand). - bench34 / bench37 (512 in, 128 out, TP=64, nextn=5): TPOT 268.2 -> 264.0 -> 234.7 ms, step 1025 -> 907 ms, TTFT 5.44 -> 5.01 s. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-25 06:06:50 +08:00
..
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
dflash.py	Neuron DSpark: draft sampling as one region graph for greedy rows; token embedding on device by default	2026-10-25 06:06:50 +08:00