NetEase-FuXi/EETQ

Issues

• Repetition with Llama3-70b and EETQ

  #22 opened 2 months ago by mjsteele12
  2

• Does it support Vision Transformers?

  #21 opened 2 months ago by PaulaDelgado-Santos
  2

• Unsupported Arch Assertion fail

  #30 opened 3 months ago by rahul3161
  1

• My system just updated CUDA to 12.6 and I can no longer compile EETQ. (Python 3.12)

  #31 opened 3 months ago by michael-newsrx
  0

• 安装之后报错

  #29 opened 3 months ago by LChuanwMz
  1

• EETQ wheel not building

  #27 opened 3 months ago by donjuanpond
  3

• EETQ-quantized TrOCR gives nonsense output

  #28 opened 3 months ago by donjuanpond
  2

• Does it support Whisper model?

  #26 opened 4 months ago by kadirnar
  2

• add Qwen2

  #24 opened 4 months ago by ehartford
  6

• Supports H100

  #12 opened 4 months ago by mwbyeon
  1

• Support CPU quantization

  #19 opened 6 months ago by xgal
  4

• ImportError: cannot import name 'EetqConfig' from 'transformers', despite using using 4.38.2 which satisfies >=4.27.0

  #23 opened 4 months ago by moruga123
  2

• How to handle bfloat16?

  #4 opened a year ago by vgoklani
  7

• Integration with Hugging Face transformers library

  #13 opened 6 months ago by younesbelkada
  2

• License

  #18 opened 6 months ago by AlpinDale
  1

• Qlora with eetq is quite slow

  #17 opened 6 months ago by hjh0119
  3

• how to dequant a EETQ model?

  #14 opened 7 months ago by mxjmtxrm
  4

• Quantization takes a very long time

  #10 opened 9 months ago by timohear
  3

• Understanding EETQ and 8 bit quantization

  #5 opened a year ago by RonanKMcGovern
  3

• Question on outlier handling

  #1 opened a year ago by 0xymoro
  1

• Why does EETQ take up all VRAM

  #3 opened a year ago by RonanKMcGovern
  2

• 安装出错ERROR: Could not build wheels for EETQ, which is required to install pyproject.toml-based projects

  #2 opened a year ago by linshuijin
  5