Commit Graph

5 Commits

Author SHA1 Message Date
6680585975 大改 2026-02-10 23:08:39 +08:00
101435817a fix: add initialize_cache method to NPU worker 2026-02-10 19:42:32 +08:00
c3631d65c2 fix: initialize TP/PP parallel groups after distributed environment 2026-02-10 19:14:29 +08:00
0765fc9fd3 fix: pass world_size int to init_distributed_environment instead of vllm_config 2026-02-10 18:58:21 +08:00
e75504df72 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
2026-02-10 11:06:01 +08:00