Skip to content

Release version 0.7.0
Compare
Choose a tag to compare
@volcacius volcacius released this 29 Oct 11:02
· 517 commits to master since this release
v0.7.0
15ecc2f

Breaking changes

  • DPUv1 specific export flow has been deprecated (since DPUv1 has been deprecated in Vitis AI).
  • Support for PyTorch < 1.5 has been deprecated.
  • The previous implementation of graph quantization has been deprecated.

Fixes

  • Issues between statistics collection in quantized activations and BREVITAS_JIT=1 should be solved.
  • Statistics collection in quantized activations is now done with a Buffer before switching to a learned Parameter, to keep things consistent in distributed training.
  • Custom ONNX functions are now properly registered with PyTorch.
  • Various other minor fixes, see full changelog below.

Features

  • Support for various more operators in QuantTensor.
  • Initial support for post-training quantization through statistics collection, bias correction, and equalization.
  • Initial support for FX-based graph quantization, currently targeting FlexML (an internal toolchain) only.
  • Various other minor enhancements, see full changelog below.

Full Changelog: v0.6.0...v0.7.0

Assets 2
Loading