Skip to content

Intel Neural Compressor Release 3.10

Latest

Choose a tag to compare

@thuang6 thuang6 released this 29 Sep 07:11
· 6 commits to main since this release
v3.10
  • Highlights
  • Features
  • Improvements
  • Validated Hardware
  • Validated Configurations

Highlights

  • NVFP4 with E5M3 scaling experimental support for PyTorch
  • Selective and mixed quantization support for Keras/JAX

Features

  • Support NVFP4 with E5M3 scaling for PyTorch (Experimental)
  • Support model-free quantization for PyTorch
  • Add dynamic fused MoE bias support for GPT-OSS model on Gaudi
  • Add vLLM QDQ plugin for accuracy benchmark based on simulation
  • Support for selective and mixed quantization in Keras/JAX, allowing different model components to remain unchanged or use different quantization methods and configurations, including static or dynamic quantization, different data types, and other quantization options
  • Support for quantization per channel for weights for Keras/JAX

Improvements

  • Security issue fixes
  • SDXL model MXFP8 PTQ example
  • Kimi K2.6 MXFP4 PTQ example
  • Minimax-M2.7 MXFP4 PTQ example

Validated Hardware 

  • Intel Gaudi Al Accelerators (Gaudi 2 and 3)
  • Intel Xeon Scalable processor (4th, 5th and 6th Gen)
  • Intel® Arc™ B-Series Graphics GPU (B60)

Validated Configurations

  • Ubuntu 24.04 & Win 11
  • Python 3.11, 3.12, 3.13
  • PyTorch 2.12, 2.13, 2.14
  • JAX 0.10

Notes

  • It is recommended to use version v3.10 or later to mitigate code CVEs.