whn09 57d373e25b Neuron chunk attention: decode the cache once, gathered_attn_idx (the #71 way) (#26) ... For a prefill chunk the per-row path decoded rows x topk KV records (128 x 640 a layer: 31.8 ms of a 49.6 ms attention region at TP=64). The chunk path now decodes each cache scope once into a bf16 table (pages x page slots, NaN-free) and the gathered_attn_idx kernel gathers each row's slots in SBUF, as vllm-neuron#71 does. Used while the caches hold <= 32768 slots (DEEPINFER_NEURON_ATTN_TABLE_SLOTS); size the pool with --num_kv_blocks. Tiny V4.1 on a NeuronCore: short 8/9, long 9/9, cos >= 0.9979. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-24 07:29:00 +08:00
..
_C	initial commit	2026-10-20 12:09:42 +08:00
distributed	initial commit	2026-10-20 12:09:42 +08:00
engine	Neuron: CP group as a replicated-decode group; MoE all-reduce mode (#28)	2026-10-23 22:46:04 +08:00
entrypoints	initial commit	2026-10-20 12:09:42 +08:00
hugging_face	Neuron: concatenate FP8 checkpoint tensors as bytes (fixes MoE on device)	2026-10-21 11:46:58 +08:00
model_executor	Neuron: head-sharded attention over the CP group (TP decode) (#28)	2026-10-23 22:53:32 +08:00
neuron_ops	Neuron chunk attention: decode the cache once, gathered_attn_idx (the #71 way) (#26)	2026-10-24 07:29:00 +08:00
npu_ops	initial commit	2026-10-20 12:09:42 +08:00
structure_output	initial commit	2026-10-20 12:09:42 +08:00
ve	initial commit	2026-10-20 12:09:42 +08:00
worker	Neuron CP followers: keep the EPLB step when skipping the sampler (#28)	2026-10-24 00:04:02 +08:00
__init__.py	Neuron basic mode: try prefill on every step	2026-10-21 21:00:54 +08:00
attrdict.py	initial commit	2026-10-20 12:09:42 +08:00
config.py	initial commit	2026-10-20 12:09:42 +08:00
environ.py	Neuron: head-sharded attention over the CP group (TP decode) (#28)	2026-10-23 22:53:32 +08:00
load_class.py	initial commit	2026-10-20 12:09:42 +08:00
logger.py	initial commit	2026-10-20 12:09:42 +08:00
model_config_loader.py	initial commit	2026-10-20 12:09:42 +08:00
multimodal_tokens.py	initial commit	2026-10-20 12:09:42 +08:00
platform.py	Neuron: static decode graphs, static-shape MoE, trn2 e4m3 fp8 (issues #9, #12, #24)	2026-10-22 11:59:37 +08:00
py.typed	initial commit	2026-10-20 12:09:42 +08:00
sampling_params.py	initial commit	2026-10-20 12:09:42 +08:00
sequence.py	initial commit	2026-10-20 12:09:42 +08:00
shared_memory.py	initial commit	2026-10-20 12:09:42 +08:00
testing.py	initial commit	2026-10-20 12:09:42 +08:00
timer.py	initial commit	2026-10-20 12:09:42 +08:00
utils.py	Neuron basic mode — part 3: end-to-end check vs the official reference	2026-10-20 20:20:02 +08:00