OpenGVLab/EfficientQAT

Issues

• Is 7B llama speed expected to be slow?

  #19 opened 19 days ago by w32zhong
  0

• Quip# inference speed in your paper is incorrect?

  #9 opened a month ago by sankeerth95
  2

• why model output is too much slow?

  #18 opened 23 days ago by dahwin
  1

• Can the results of the quantification process be saved?

  #17 opened a month ago by QB-Chen
  1

• Question about calib datasets.

  #16 opened a month ago by mxjmtxrm
  3

• GGUF

  #3 opened 2 months ago by maxim-saplin
  8

• block_ap过程中似乎不能使用多卡并行，老是爆显存

  #15 opened a month ago by QB-Chen
  1

• Cohere Command R Plus

  #10 opened a month ago by Khaledhesham
  1

• Data arrangement

  #7 opened a month ago by yancaoweidaode
  4

• How to do e2e_qp with multi-GPU?

  #14 opened a month ago by mxjmtxrm
  1

• DATA FOR TRAINING

  #12 opened a month ago by LiMa-cas
  1

• Loss is nan

  #6 opened a month ago by mxjmtxrm
  4

• Reproduce Llama2-7b

  #13 opened a month ago by laomao0
  5

• Evaluation pipeline points to missing files

  #11 opened a month ago by snps-tonatiuh
  2

• question about real quant

  #4 opened a month ago by mxjmtxrm
  6

• Can not reproduce the results

  #8 opened a month ago by LiuSiQi-TJ
  2

• Any experiments on w4a16 with group_size=-1( no group)?

  #2 opened 2 months ago by brisker
  4

• dimension mismatch error.

  #5 opened 2 months ago by mxjmtxrm
  0