tpoisonooo/llama.onnx

Issues

• Llama模型转完ONNX之后，输入可以是input_embeds吗

  #30 opened 3 months ago by OswaldoBornemann
  0

• Error in converting llama

  #29 opened 5 months ago by purejomo
  0

• llama => onnx => tensorrt

  #28 opened a year ago by tp-nan
  0

• 一种改进next_token计算的方式

  #27 opened a year ago by luchangli03
  1

• 如何分段转换llama模型为onnx？

  #26 opened a year ago by jxcomeon
  5

• GPU Inference

  #25 opened a year ago by tpoisonooo
  3

• Could you add torch.onnx.export() in tools/export-onnx.py

  #20 opened 2 years ago by foreveronehundred
  2

• cannot import name 'MemoryPoolSimple' from 'public'

  #23 opened a year ago by JiangFeng07
  1

• onnx模型推理

  #21 opened 2 years ago by KaiyuHu2001
  1

• 请问如何支持batch的推理？

  #22 opened a year ago by VincentJYZhang
  1

• transfer fp32 to fp16 error

  #18 opened 2 years ago by Ted8000
  0

• 7B onnx模型(float16) 占用显存超过32G

  #19 opened 2 years ago by iamhere1
  0

• Inference with GPU took too much GPU RAM

  #16 opened 2 years ago by DungMinhDao
  4

• Alternative RWKV onnx converter

  #17 opened 2 years ago by harrisonvanderbyl
  1

• Inference super slow

  #15 opened 2 years ago by SinanAkkoyun
  4

• 关于ONNX转换

  #9 opened 2 years ago by lingffff
  17

• demo_llama.py: No module named public

  #14 opened 2 years ago by SinanAkkoyun
  1

• convert Onnx problem

  #12 opened 2 years ago by xcxhy
  11

• Maybe some thing wrong with the script "demo_single.py"

  #11 opened 2 years ago by yingzhao27
  3

• some questions about llama.onnx

  #3 opened 2 years ago by dvc94ch
  13