Agent Backend Adapter

自动化适配Agent后端,集成MSRL(MindSpeed-RL)、VERL、VLLM等训练推理框架。When users need to integrate training frameworks (MindSpeed-RL/VERL) with inference engines (vLLM), configure agent backend pipelines, generate training scripts, create adapter wrappers, or build complete training-inference pipelines for LLM agents, use this skill. Supports GRPO/PPO training algorithms, multi-NPU distributed inference on Ascend NPUs, and standalone code generation independent of OpenCode. This skill is optimized for Ascend NPU (昇腾) hardware.

ascend Updated 58 repo stars

File contents

ascend/mindsdk-referenceapps commit 5e9067a295

Frequently asked questions

npx get-skill add ascend/agent-backend-adapter