Accelerator Scenarios
This chapter covers end-to-end inference scenarios on domestic / heterogeneous accelerators (such as Huawei Ascend and Hygon). For general inference image, template, and deployment operations, see AI Inference.
Scenario Overview
| Scenario | Description |
|---|---|
| Run DeepSeek V4 Flash on Huawei Ascend NPU | Deploy DeepSeek-V4-Flash with vLLM Ascend on Huawei Ascend NPU |
| Hygon GPU | Platform support is available; for general inference operations, see AI Inference |
Run DeepSeek V4 Flash on Ascend NPU
Overview