9 lines
238 B
Markdown
9 lines
238 B
Markdown
|
# SNPE feature support
|
||
|
|
||
|
Currently mmdeploy integrates the onnx2dlc model conversion and SDK inference, but the following features are not yet supported:
|
||
|
|
||
|
- GPU_FP16 mode
|
||
|
- DSP/AIP quantization
|
||
|
- Operator internal profiling
|
||
|
- UDO operator
|