DeepInfer/build.sh
whn09 ed49792a0c Add AWS Trainium (Neuron) platform, basic mode — part 1
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>
2026-10-20 18:34:51 +08:00

28 lines
620 B
Bash
Executable File

#!/bin/bash
set -euo pipefail
case "${DEEPINFER_ACCELERATOR:-}" in
nvidia|ascend|neuron) ;;
*)
echo "Usage: DEEPINFER_ACCELERATOR=nvidia|ascend|neuron $0" >&2
exit 1
;;
esac
# Install other Python dependencies
pip install -r "requirements-${DEEPINFER_ACCELERATOR}.txt"
if [ "${DEEPINFER_ACCELERATOR}" = nvidia ]; then
# Patch NCCL to 2.32.3
pip install --no-deps --force-reinstall nvidia-nccl-cu13==2.32.3
fi
# Build and install vendored dependencies
bash ./scripts/build_vendor.sh
# Build DeepInfer
bash ./scripts/build.sh build
echo "✅ DeepInfer is successfully built"