Skip to content

Issues: InternLM/lmdeploy

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
325 Open 1,268 Closed
325 Open 1,268 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

使用locust时发现的问题
#417 opened Sep 14, 2023 by frankxyy updated Sep 19, 2023
1
[Bug] llama2-70B NTK，输入长度只能支持到8K？
#479 opened Sep 26, 2023 by sjzhou4 updated Sep 27, 2023
2 tasks done
@lzhangzz
6
[Deploy Error] ValueError: If eos_token_id is defined, make sure that pad_token_id is defined.
#522 opened Oct 1, 2023 by vansin updated Oct 11, 2023
@grimoire
3
[Bug] int4 awq kernel
#498 opened Sep 27, 2023 by liang872 updated Oct 11, 2023
2 tasks done
@lzhangzz
codellama-Instruct版本地测试运行和服务部署返回的结果不一致
#579 opened Oct 18, 2023 by for-just-we updated Oct 19, 2023
1 of 2 tasks
@lvhan028
[Feature] may support Mistral-7B recently? whatever Turbomind or Pytorch backlog
#534 opened Oct 9, 2023 by varuy322 updated Oct 26, 2023
kv int8 量化， 能较少显存，吞吐基本没有提升？
#621 opened Oct 27, 2023 by seeyourcell updated Oct 30, 2023
5
精度损失很多
#617 opened Oct 26, 2023 by seeyourcell updated Nov 1, 2023
4
[Bug] "cos_cached" shape incorrect error.
#664 opened Nov 8, 2023 by WarrenZhao updated Nov 8, 2023
2 tasks
@pppppM
支持多长输入 TurboMind supports Qwen-7B, dynamic NTK-RoPE scaling and dynamic logN scaling
#430 opened Sep 19, 2023 by yuanjie-ai updated Nov 14, 2023
3
[Feature] how to open window attention in qwen-14B? backlog
#638 opened Nov 2, 2023 by amulil updated Nov 17, 2023
4
[Feature] Any Plan to implement INT8 weight-only quantizaton
#703 opened Nov 17, 2023 by yunzhongyan0 updated Nov 17, 2023
@pppppM
4
[Feature] 支持frequency_penalty采样 backlog
#704 opened Nov 17, 2023 by RytonLi updated Nov 19, 2023
[Bug] The GPU memory doesn't change after changing batch_size
#731 opened Nov 22, 2023 by hxdbf updated Nov 22, 2023
2 tasks
@lzhangzz
3
【Design Questinon】any plan to decouple batching and cache from llama? backlog
#476 opened Sep 26, 2023 by jinuxstyle updated Nov 23, 2023
@lzhangzz
1
[bug] group_size = 64 has bug backlog
#322 opened Aug 28, 2023 by lippman1125 updated Dec 11, 2023
@irexyc
5
报名参加书生·浦语大模型实战营——两周带你玩转微调部署评测全链路
#890 opened Dec 26, 2023 by vansin updated Dec 26, 2023
使用Qwen-7B 32K长度推理，不出结果（都是空）
#883 opened Dec 22, 2023 by CocaColaKing updated Dec 27, 2023
@lzhangzz
4
[Performance] How many gains does Interactive Inference Mode contribute to the throughput?
#565 opened Oct 17, 2023 by nullxjx updated Jan 10, 2024
@lvhan028
1
想请教怎么往kv cache中添加缓存信息
#994 opened Jan 19, 2024 by WCwalker updated Jan 19, 2024
@grimoire
2
[Question]请问这里的有关grid norm的计算逻辑有什么理论指导吗？
#1014 opened Jan 22, 2024 by rightchose updated Jan 22, 2024
@lzhangzz
internLM2 20B长本文部署后，调用接口异常
#1078 opened Jan 31, 2024 by testTech92 updated Feb 2, 2024
2 tasks
@irexyc
6
[RFC] Refactor chat template and remove model name from engine config RFC
#1065 opened Jan 30, 2024 by AllentDan updated Feb 5, 2024
1
5
[Docs] presence_penalty设置无效
#1046 opened Jan 26, 2024 by RytonLi updated Feb 6, 2024
5
[Bug] 使用internlm2-chat-7b 微调后的自制模型，4bit量化后无法使用
#1109 opened Feb 3, 2024 by zhanghui-china updated Feb 6, 2024
2 tasks done
@pppppM
11
ProTip! no:milestone will show everything without a milestone.