whn09 3629d113fb Neuron: prompt chunks through the decode region graphs (issue #26) ... - PrepareArgs.prompt_as_decode: decode-layout metadata for a prompt chunk; input_ids are the prompt's own tokens instead of last token + MTP drafts. - DEEPINFER_NEURON_PREFILL_BUCKET adds one graph size; the model runner pads a prompt chunk to it with the decode placeholders (every EP rank takes the same bucket, so the static collectives match). Sampling still sees a prompt step. - nki_attention.paged_mqa_logits: one gather + one kernel call for a chunk (one sequence) instead of a T-way loop. - bf16 linear for the LM head eagerly on a NeuronCore (b.float() was a 2.6 GiB copy a call); DEEPINFER_NEURON_REGION_TIMING; --num_prompts. Host mode, tiny V4.1, chunk 128: same tokens as eager prefill (short 9/9, long 715 tokens in 6 chunks 8/9 against golden). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-23 03:19:56 +08:00
..
engine	Neuron: prompt chunks through the decode region graphs (issue #26)	2026-10-23 03:19:56 +08:00
graph_timer	Add AWS Trainium (Neuron) platform, basic mode — part 1	2026-10-20 18:34:51 +08:00
utils	initial commit	2026-10-20 12:09:42 +08:00
asc_utils.cpp	initial commit	2026-10-20 12:09:42 +08:00
cuda_utils.cpp	initial commit	2026-10-20 12:09:42 +08:00
cuda_utils.hpp	Add AWS Trainium (Neuron) platform, basic mode — part 1	2026-10-20 18:34:51 +08:00
neuron_utils.cpp	Add AWS Trainium (Neuron) platform, basic mode — part 1	2026-10-20 18:34:51 +08:00
pybind.cpp	initial commit	2026-10-20 12:09:42 +08:00