AXKuhta / rwkv-onnx-dml

Run ONNX RWKV-v4 models with GPU acceleration using DirectML [Windows], or just on CPU [Windows AND Linux]; Limited to 430M model at this time because of .onnx 2GB file size limitation

Geek Repo

Github PK Tool

Note

Use Fabrice Bellard's ts_server instead if you are looking for fast CPU inference

About

Run ONNX RWKV-v4 models with GPU acceleration using DirectML [Windows], or just on CPU [Windows AND Linux]; Limited to 430M model at this time because of .onnx 2GB file size limitation

Languages

Language:C++ 85.9%Language:C 13.6%Language:Makefile 0.3%Language:Batchfile 0.1%