IntelLabs/FP8-Emulation-Toolkit

Issues

• load datasets error in FP8 training for BERT

  #17 opened a month ago by fmo-mt
  0

• Pascal support

  #16 opened 2 months ago by chaiebnadhem
  0

• Why does the quantized value still exceed the range of FP8 representation?

  #15 opened 3 months ago by adfad1
  0

• Could you briefly explain what does those in modes mean?

  #14 opened 3 months ago by pyjhzwh
  1

• How library completes backend support / Why the quantized models show no difference.

  #8 opened 6 months ago by xuann6
  2

• reproduction of results on "FP8 Format for Deep learning"

  #13 opened 7 months ago by amine-ammor
  0

• TypeError: zeros_like(): argument 'input' (position 1) must be Tensor, not NoneType

  #12 opened 7 months ago by Siris-Limx
  1

• Using GPU and Still Get: Illegal instruction (core dumped)

  #7 opened 7 months ago by xuann6
  5

• No module named 'fpemu_cpp'

  #9 opened 8 months ago by hailuu684
  0

• PTQ for BERT

  #2 opened a year ago by qingswu
  2

• examples/inference/bert readme instructions for FP8

  #6 opened a year ago by willwray
  5

• Illegal instruction (core dumped)

  #3 opened a year ago by julianfaraone
  6

• Segfault

  #1 opened a year ago by tjingrant
  3