whn09 9c8c85d83d Neuron: per-layer region graphs + vllm-neuron#71 NKI kernels (issues #10, #11, #13, #25) ... - Decode runs eagerly and compiles per-layer regions (attention half, MoE) with stage boundaries (neuron_ops/regions.py, DEEPINFER_NEURON_GRAPH_MODE=regions); layer KV views are sliced from the roots inside the graph (_LazyKVCache). - vllm-neuron#71 NKI kernels (Apache-2.0, vendored under neuron_ops/nki/ with attribution), called via torch_neuronx.nki_hop.wrap_nki: blockquant (fp8/fp4 GEMMs incl. grouped einsum, MoE and shared expert on bf16 activations), sparse_attn / index_score / compress_pool (nki_attention.py), hc_mixes / hc_expand / hc_collapse / hc_attn_out / rmsnorm / swiglu (nki_hc.py, nki_norm.py). - Compile-safe formulations: row-major scales, no dtype bitcasts of graph inputs (uint8 weight tensors), whole-row KV stores, byte assembly in int32 narrowed once at the store, arithmetic int16 scale packing, plain fma/rsqrt and bf16 F.linear under compile; default backend deepinfer_neuron (torch fp8 carried as uint8, avoiding NCC_EOCP001 with the kernels' OCP fp8). - Host: tiny model 9/9 vs golden on all prompts; device: kernel tests pass (13 attention, 88 hc/norm); region decode graph compiles except the attention projection stage (being reduced). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-22 17:36:54 +08:00
..
distributed	initial commit	2026-10-20 12:09:42 +08:00
engine	initial commit	2026-10-20 12:09:42 +08:00
models	initial commit	2026-10-20 12:09:42 +08:00
neuron	Neuron: per-layer region graphs + vllm-neuron#71 NKI kernels (issues #10, #11, #13, #25)	2026-10-22 17:36:54 +08:00
ve	initial commit	2026-10-20 12:09:42 +08:00
worker	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
conftest.py	initial commit	2026-10-20 12:09:42 +08:00
test_cuda_sync_guards.py	initial commit	2026-10-20 12:09:42 +08:00