owenliang/qwen-vllm

Issues

• jetson的盒子可以安装vllm吗

  #10 opened 3 months ago by KungFuPandaPro
  0

• vllm推理提速不明显，如何解决？

  #7 opened 8 months ago by zzyzeyuan
  3

• 运行vllm_offline.py报错

  #8 opened 8 months ago by zjjznw123
  3

• 流式处理如何实现批量推理？

  #9 opened 7 months ago by Simple6K
  0

• 请问本仓库的vllm是哪一个版本的？

  #5 opened 8 months ago by zzyzeyuan
  0

• 后续是否会支持多个prompts一起送入model.generate()?

  #6 opened 8 months ago by zzyzeyuan
  0

• 请问是否支持Qwen1.5系列模型（不同量化方式 / 非量化）

  #2 opened 9 months ago by tomFoxxxx
  6

• lora加载如何实现

  #3 opened 9 months ago by nlp-learner
  1