whn09 cc90926a1c Neuron: full DeepSeek-V4.1-Flash loads and prefills on 64 NeuronCores (EP=64) ... Device-memory fixes found bringing up the released checkpoint (16.45 GiB of weights per 24 GB core): - Engram: the Neuron EngramBuffer keeps only this rank's SF rows, so skip the all-gather of the replicated SF table (~3 GB per layer, allocated on the device -> "Failed to allocate resource"). - gather_tl: index_select / advanced indexing of an int8 table allocates several times the table on the device (+4.9 GiB for the 1.3 GB embedding); gather through F.embedding on an int32 / fp16 view instead (bit-exact, no extra memory). - deep_gemm FP8/FP4 GEMMs: dequantize the weight in N chunks of 32M elements and one expert at a time instead of whole projections / all local experts in fp32 (OOM on a fragmented pool); bit-identical results. - transfer_to_neuron: import torch.utils._device explicitly (missing when torch_neuronx is not auto-loaded). examples/neuron/offline_inference_neuron.py: offline inference in basic mode (text prompts, no MTP / EPLB, fixed KV pool, max_model_len >= 2048 * 8 for the candidate-block filter), one process per NeuronCore. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-21 14:57:51 +08:00
..
mtp	initial commit	2026-10-20 12:09:42 +08:00
v4_modules	Neuron: full DeepSeek-V4.1-Flash loads and prefills on 64 NeuronCores (EP=64)	2026-10-21 14:57:51 +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	initial commit	2026-10-20 12:09:42 +08:00
deepseek_vl.py	initial commit	2026-10-20 12:09:42 +08:00
deepseek.py	initial commit	2026-10-20 12:09:42 +08:00