wehub-resource-sync
8 lines
243 B
Markdown
8 lines
243 B
Markdown
|
|
|
|
|
|
|
|
- 代码：https://github.com/NVIDIA/TensorRT-Model-Optimizer
|
|
- 文档：https://nvidia.github.io/TensorRT-Model-Optimizer/
|
|
|
|
- 量化方法最佳实践：https://nvidia.github.io/TensorRT-Model-Optimizer/guides/_choosing_quant_methods.html |