01/ 01
- TensorRT and ONNX optimization - Quantization (FP16, INT8) - Model distillation - Caching and incremental generation - Pipeline parallelism
自动翻译
自动翻译中…
- TensorRT and ONNX optimization - Quantization (FP16, INT8) - Model distillation - Caching and incremental generation - Pipeline parallelism
自动翻译中…
还没有评论,来抢沙发吧