whn09 f9cbf6f2e5 Neuron: CP group as a replicated-decode group; MoE all-reduce mode (#28) ... - Followers claim core cp_rank (DEEPINFER_NEURON_LOCAL_RANK at spawn) and get the graph's host metadata through shm (no in-graph broadcast on Neuron), including the prompt-as-decode bucket and the context limit; they skip the sampler. max_num_prefilling_tokens is not divided by cp on Neuron (prompt chunks run replicated). - DEEPINFER_NEURON_NUM_KV_BLOCKS: the fixed KV pool as an env var, so spawned CP followers take it too. - static MoE: when the EP group is the CP group the tokens are already replicated: no all-gather, all-reduce instead of reduce-scatter (64x fewer expert rows a rank at cp=ep=64). - run_deepinfer_tiny.py --cp. Host tiny: cp=2 and cp=4 match the cp=1 tokens (short 8/9 at a near tie, long 9/9). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-23 22:46:04 +08:00
..
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
base.py	Neuron: CP group as a replicated-decode group; MoE all-reduce mode (#28)	2026-10-23 22:46:04 +08:00
cache_engine.py	Neuron: separate state regions, chunk-wide indexer context (issue #26)	2026-10-23 03:46:56 +08:00
cuda_graph_runner.py	initial commit	2026-10-20 12:09:42 +08:00
decode_perf_cache.py	initial commit	2026-10-20 12:09:42 +08:00
dflash_cuda_graph_runner.py	initial commit	2026-10-20 12:09:42 +08:00
model_runner.py	Neuron: CP group as a replicated-decode group; MoE all-reduce mode (#28)	2026-10-23 22:46:04 +08:00
neuron_graph_runner.py	Neuron: split region graphs for prefill chunks only (#26)	2026-10-23 21:39:56 +08:00
runtime_config.py	initial commit	2026-10-20 12:09:42 +08:00
worker.py	initial commit	2026-10-20 12:09:42 +08:00
zos_status.py	initial commit	2026-10-20 12:09:42 +08:00