Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / owenliang/qwen-vllm issues and pull requests
#11 - 多轮对话怎么实现kv_cache加速的呢,在这个项目中,每次调用chat会开启kv_cache吗
Issue -
State: open - Opened by HaoRenkk123 3 months ago
#10 - jetson的盒子可以安装vllm吗
Issue -
State: open - Opened by KungFuPandaPro 5 months ago
#9 - 流式处理如何实现批量推理?
Issue -
State: open - Opened by Simple6K 9 months ago
#8 - 运行vllm_offline.py报错
Issue -
State: closed - Opened by zjjznw123 10 months ago
- 3 comments
#7 - vllm推理提速不明显,如何解决?
Issue -
State: open - Opened by zzyzeyuan 10 months ago
- 3 comments
#6 - 后续是否会支持多个prompts一起送入model.generate()?
Issue -
State: open - Opened by zzyzeyuan 10 months ago
#5 - 请问本仓库的vllm是哪一个版本的?
Issue -
State: closed - Opened by zzyzeyuan 10 months ago
#4 - 适配Qwen1.5模型
Pull Request -
State: open - Opened by tomFoxxxx 11 months ago
- 1 comment
#3 - lora加载如何实现
Issue -
State: open - Opened by nlp-learner 11 months ago
- 1 comment
#2 - 请问是否支持Qwen1.5系列模型(不同量化方式 / 非量化)
Issue -
State: open - Opened by tomFoxxxx 11 months ago
- 6 comments
#1 - Abstract into different methods
Pull Request -
State: open - Opened by xxw1995 11 months ago