feat: initial vllm-npu-plugin for Ascend NPU adaptation

- NPUPlatform: device management, HCCL process group, config adaptation
- AscendAttentionBackend: npu_fusion_attention (prefill) + npu_incre_flash_attention (decode)
- NPUCommunicator: HCCL-based distributed communication
- NPUWorker: NPU device init, memory profiling
- Custom ops: SiluAndMul, RMS norm, rotary embedding
- Plugin registered via vllm.platform_plugins entry point

Based on vllm-ascend official pattern, targeting Ascend 910B
This commit is contained in:
2026-02-10 11:06:01 +08:00
commit e75504df72
15 changed files with 1344 additions and 0 deletions

1
vllm_npu/ops/__init__.py Normal file
View File

@@ -0,0 +1 @@
"""Ascend NPU custom op registrations."""