whn09 e6c7d7867a Neuron: sampling flags read once a step; runtime profiling on the driver only; one-lookup embedding ... - fused_sample._host_flags: the top-p/top-k and greedy flags of the step's sampling parameters are read from the device once a step (a DSpark step samples the same tensors six times); reset_host_flags at each sample step. - NEURON_RT_INSPECT_* stays on the driver (64 ranks would overwrite one output directory). - VocabParallelEmbedding.ids_in_range: one F.embedding instead of the zero-filling gather (~5 eager NEFF launches). - bench33 (512 in, TP=64, nextn=5): TPOT 272.6 -> 268.2 ms. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-25 03:52:47 +08:00
..
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
arg_utils.py	initial commit	2026-10-20 12:09:42 +08:00
engine_type.py	initial commit	2026-10-20 12:09:42 +08:00
llm_engine.py	Neuron: sampling flags read once a step; runtime profiling on the driver only; one-lookup embedding	2026-10-25 03:52:47 +08:00
profile_server.py	initial commit	2026-10-20 12:09:42 +08:00
stats_logger.py	initial commit	2026-10-20 12:09:42 +08:00