search

microsoft / DirectML

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.
MIT License
2.25k stars 300 forks source link

Operator 'aten::multinomial' is not currently supported on the DML backend #372

Open ehartford opened 1 year ago

ehartford commented 1 year ago

I was trying to implement the simple Shakespeare model using DirectML and got this message:

UserWarning: The operator 'aten::multinomial' is not currently supported on the DML backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at D:\a\_work\1\s\pytorch-directml-plugin\torch_directml\csrc\dml\dml_cpu_fallback.cpp:16.)
  idx_next = torch.multinomial(probs, num_samples=1)
linnealovespie commented 1 year ago

Hi @ehartford, thanks for reaching out. We'll add aten::multinomial to our backlog. You can check out our Operator Roadmap to see what we operators we currently support.