Xiuyu-Li/q-diffusion

Issues

• Activation quantization of Stable Diffusion.

  #2 opened 2 years ago by jianyuheng
  1

• [Request] Code for calibration dataset generation and Generic code for any diffusion model

  #40 opened 4 months ago by Ali-Flt
  1

• Support for Facebook DiT

  #39 opened 4 months ago by Ali-Flt
  0

• how to use deepspeed to train qdiffusion on SD?

  #38 opened 5 months ago by 2524378044
  0

• Q-Diffusion support for Stable Diffusion XL (CPU)

  #36 opened 9 months ago by badhri-intel
  1

• Why this quantization model need more than 24GB GPU memory which is larger than ideal 500M?

  #14 opened a year ago by felixslu
  4

• Stable diffusion generated samples using quantized checkpoint looks strange

  #31 opened a year ago by colorjam
  2

• 如何获取量化参数

  #28 opened a year ago by miaott1234
  2

• Tensorrt employ the q-diffusion's recontruction method to quantize SD-XL?

  #37 opened 8 months ago by hanhanpp
  0

• How to do it in SDXL-turbo?

  #35 opened 10 months ago by ApolloRay
  0

• Does q-diffusion work on SDXL?

  #22 opened 10 months ago by TruthSearcher
  3

• 'functions' package error & how to extract FID

  #34 opened 10 months ago by parkjjoe
  0

• Can you please add a tutorial on quantification to the README？

  #33 opened 10 months ago by ningmenghongcha
  0

• End-to-End Quantization for Speedup and Memory Savings: Inviting Contributions!

  #23 opened a year ago by Xiuyu-Li
  2

• Why w4a8 quantization method have not accelerate the inferrence speed of Stable Diffusion models?

  #15 opened 10 months ago by felixslu
  2

• About the quantized model

  #12 opened 10 months ago by shiyuetianqiang
  0

• Extremely high VRAM usage

  #7 opened 10 months ago by easonoob
  2

• Inference speed mechanism or Model size compression ?

  #1 opened 10 months ago by sravanthOppo27
  7

• BOPs measurement

  #32 opened 10 months ago by rocco-manz
  0

• How to deploy in an environment without GPUs?

  #30 opened a year ago by loonglongdada
  0

• Compatibility with MacOSX?

  #29 opened a year ago by nachiket
  0

• Why quant QKMatMul as a block while it has no submodule?

  #26 opened a year ago by Sugar929
  6

• Model sizes

  #19 opened a year ago by prinshul
  1

• QDiffusion for Stable Diffusion

  #27 opened a year ago by stein-666
  0

• What is the minimum number of datasets that meet the requirements of text-to-image calibration?

  #25 opened a year ago by hanhanpp
  0

• calibration datasets

  #21 opened a year ago by hanhanpp
  0

• errors in executing in LSUN-bed w8a8 quantization

  #24 opened a year ago by Sugar929
  0

• Would you please provide the parameters for the LSQ and the block reconstruction? Thanks a lot

  #18 opened a year ago by yuzheyao22
  1

• Code for model calibration

  #10 opened a year ago by Cheeun
  5

• Open-source more code?

  #17 opened a year ago by lingffff
  1

• Error: No such file or directory: 'models/ldm/stable-diffusion-v1/model.ckpt'

  #13 opened a year ago by felixslu
  1

• Question about the inference process

  #16 opened a year ago by JiaojiaoYe1994
  0

• Calibration Process in the 'resume_cali_model' Function

  #5 opened a year ago by wangjialinEcopia
  4

• load cifar_w8a8_ckpt.pth

  #11 opened 2 years ago by foreverlove944
  4

• Loading quantized model checkpoint error

  #8 opened 2 years ago by arthursunbao
  1

• 模型大小

  #9 opened 2 years ago by ZhibinPeng
  1

• Images are broken in readme.md

  #6 opened 2 years ago by 6174
  1

• What is the main comparison of the paper

  #4 opened 2 years ago by sravanthOppo27
  1

• the weight format of w4a8 is fp32?

  #3 opened 2 years ago by gongqiang
  1