Skip to content

zentorch Release v5.0

Latest
Compare
Choose a tag to compare
@kiriti-pendyala kiriti-pendyala released this 15 Nov 13:05

zentorch is compatible with base versions of PyTorch v2.0 or later. This release provides zentorch for PyTorch v2.4.0.
This release of the plug-in supports:

  • Datatypes FP32, BF16, and INT4 (WOQ)
  • Introduction of a new zentorch.llm.optimize() method for Hugging Face Generative LLM models
  • New zentorch.load_woq_model() method to support loading of Weight Only Quantized models generated through the AMD Quark tool. This method only supports models quantized and exported with per-channel quantization using the AWQ algorithm.
  • Improved graph optimizations, enhanced SDPA (Scalar Dot Product Attention) operator and more.
  • Automatic Mixed Precision (AMP) between FP32 and BF16 providing a performance improvement with minimal changes in accuracy