search

Vocinity / context-scorer

0 stars 1 forks source link

Release fp16 & int8 ONNX 3080 models for all GPT models #4

Closed isgursoy closed 2 years ago

isgursoy commented 2 years ago

Currently only GTX960M optimized fp32 distilgpt2 model is released. https://github.com/microsoft/onnxruntime/issues/7037#event-5836678770