whn09 45e1e44444 Neuron: tiny-model decode region graphs compile and run on a NeuronCore (issues #9, #25) ... Fixes found by reducing neuronx-cc NCC_IINL902 crashes to minimal reproducers (crash rates over repeated compiles, the compiler is nondeterministic on these graphs): - uint8 byte assembly of narrowed values (KV records, e2m1/e4m3 codes, ue8m0 exponents) crashed or silently corrupted bytes: producers keep int32 codes under compile and stores narrow once (fused_transform, kv_quant, store_kv_cache; neuron_compile.encode_codes). - int16 packed scales written through a uint8 view and read back in the same graph: the Neuron kernel now receives the int16 storage and packs byte pairs arithmetically (_alloc_quant, return_quant). - fp8 legalization pass treated plain float->bf16 conversions as fp8 carriers (wrong values + crash). - Projection stage split further (nullcontext instead of a disabled CP session). Device (tiny model, regions mode): every decode graph compiles; argmax vs golden short 9/9, medium 8/9 (step 6 near-tie, margin 0.065), long 9/9, cos 0.997-0.9995. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-22 18:38:01 +08:00
..
mtp	initial commit	2026-10-20 12:09:42 +08:00
v4_modules	Neuron: tiny-model decode region graphs compile and run on a NeuronCore (issues #9, #25)	2026-10-22 18:38:01 +08:00
vision_encoder	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
decoder_layer.py	Neuron: per-layer region graphs + vllm-neuron#71 NKI kernels (issues #10, #11, #13, #25)	2026-10-22 17:36:54 +08:00
deepseek_vl.py	initial commit	2026-10-20 12:09:42 +08:00
deepseek.py	Neuron: static decode graphs, static-shape MoE, trn2 e4m3 fp8 (issues #9, #12, #24)	2026-10-22 11:59:37 +08:00