mirror of
https://github.com/deepseek-ai/DeepInfer.git
synced 2026-10-28 23:07:09 +08:00
Run DeepInfer on the native torch-neuronx device (PrivateUse1 `neuron`, torch-neuronx 2.14, no torch-xla), following the Ascend port's structure. - deep_cluster: Neuron discovery (one DeepInfer device = one logical NeuronCore, NEURON_RT_VISIBLE_CORES, NUMA from neuron-ls). - PlatformNeuron: takes the Ascend (is_npu) kernel layouts, adds is_neuron; DEEPINFER_NEURON_DEVICE=cpu runs the same code on the host for correctness work. - neuron_ops/transfer_to_neuron: map "cuda" devices, torch.device and torch.cuda.* onto neuron:0 (counterpart of torch_npu transfer_to_npu). - C++ extension: -DWITH_NEURON host-only build; torch-allocated buffers and tensor-view slot copies instead of raw device-pointer copies. - Pure-torch drop-in vendor packages (Ascend API semantics): deep_gemm, flash_mla, deep_select, tile_kernels, tilelang (constants only). - tilelang_ops/neuron backend: KV cache / metadata / norm / compress kernels; CP, ZOS and VL entry points raise NotImplementedError. - Basic mode defaults on Neuron: eager, no DSpark/MTP drafting, no zero-overhead scheduling; MoE avoids the GPU-only mega kernel; mHC prenorm GEMM uses the Ascend single-split reduction. Not yet included: deep_ep, the sampling kernels, end-to-end harness. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| input_metadata | ||
| block_manager.hpp | ||
| flops_estimator.hpp | ||
| mtp_varlen.hpp | ||
| outputs.hpp | ||
| prepare_sample.cpp | ||
| prepare_sample.hpp | ||
| process_output.hpp | ||
| pybind_output.cpp | ||
| pybind_scheduler.cpp | ||
| pybind_sequence.cpp | ||
| pybind.cpp | ||
| pybind.hpp | ||
| scheduler.hpp | ||
| sequence.hpp | ||
| utils.hpp | ||
| zos.cpp | ||
| zos.hpp | ||