mirror of
https://github.com/handsomezhuzhu/vllm-npu-plugin.git
synced 2026-02-20 11:42:30 +00:00
handsomezhuzhu
e75504df72
- 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
13 lines
364 B
Python
13 lines
364 B
Python
"""
|
|
vllm_npu — Ascend NPU platform plugin for vLLM.
|
|
|
|
The ``register()`` function is discovered by vLLM through the
|
|
``vllm.platform_plugins`` entry-point and returns the fully-qualified
|
|
class name of the platform implementation.
|
|
"""
|
|
|
|
|
|
def register():
|
|
"""Return the fully-qualified name of the NPU platform class."""
|
|
return "vllm_npu.platform.NPUPlatform"
|