megvii-research/Sparsebit

Issues

• implementation for FQ-ViT

  #107 opened 2 years ago by shuyuan-wang
  3

• torchvision densenet121 无法转成 sparsebit QuantModel

  #102 opened 2 years ago by work-zhangzhe
  4

• errors using qViT.onnx to do inference

  #148 opened a year ago by yuhuixu1993
  1

• I wonder if the qlora do not support quantized models with groupsize!=-1

  #147 opened a year ago by yuhuixu1993
  2

• 我对你们的2080ti pipeline很感兴趣

  #143 opened 2 years ago by wesleysanjose
  2

• error when running generate.py under alpaca-lama

  #139 opened 2 years ago by wesleysanjose
  1

• Error in QAT train with DDP mode.

  #130 opened 2 years ago by zhishao
  2

• KeyError: 'onnx::QuantizeLinear_711'

  #124 opened 2 years ago by hyaihjq
  0

• RuntimeError: Ninja is required to load C++ extensions

  #123 opened 2 years ago by hyaihjq
  0

• swin transformer

  #119 opened 2 years ago by shuyuan-wang
  1

• torchvision mobilenet_v2 导出 4w4f onnx 报错

  #111 opened 2 years ago by work-zhangzhe
  0

• encounter keyerror when inputing module

  #58 opened 2 years ago by 42Shawn
  5

• QAT cifar10 example with QADD Quant enable 报错

  #94 opened 2 years ago by work-zhangzhe
  1

• QAT cifar10 example 报错

  #91 opened 2 years ago by work-zhangzhe
  1

• How could I reproduce the results of QAT_DeiT on ImageNet?

  #68 opened 2 years ago by KenRamzes
  2

• A bug may have been resolved.

  #51 opened 2 years ago by haiduo
  3

• will support lower bit quantization?

  #48 opened 2 years ago by www516717402
  2

• How to deal with layers constructed by bool operations?

  #57 opened 2 years ago by 42Shawn
  1

• Should we install a full-version cuda instead of an anaconda-version cuda-toolkit?

  #56 opened 2 years ago by 42Shawn
  1

• An error about "x_dq = self._forward(x, scale, zero_point) "

  #50 opened 2 years ago by haiduo
  1

• ImportError

  #49 opened 2 years ago by haiduo
  1

• update quantizer preprocess when export onnx

  #45 opened 2 years ago by PeiqinSun
  0

• error raisedfrom sparsebit.quantization import QuantModel, parse_qconfig

  #17 opened 2 years ago by wslgqq277g
  5

• error in homework Q3 code.

  #30 opened 2 years ago by szhangNJU
  3

• Dimension mismatch when QAT model export to onnx

  #22 opened 2 years ago by SuperbTUM
  1

• QTP for swin transformer

  #11 opened 2 years ago by Linaom1214
  2

• Import Error

  #18 opened 2 years ago by hsvlab
  5

• ONNX can not be loaded by Tensorrt 8.2.5& 8003

  #16 opened 2 years ago by lemuelGGG
  4

• English Docs

  #3 opened 2 years ago by fcakyon
  2

• 文档链接打不开

  #4 opened 2 years ago by liuxubit
  2