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

357 Open 1,314 Closed
357 Open 1,314 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

[Bug] pipeline 加载模型时无限期挂起 而命令行部署正常
#3107 opened Jan 31, 2025 by NB-Group
3 tasks done
2
[Bug] 如何提前终止流式推理pipe.stream_infer
#3106 opened Jan 31, 2025 by youyc22
3 tasks done
3
Deepseek R1 671b 版本的cpu部署
#3105 opened Jan 31, 2025 by infiniteYuanyl
Closing PyTorchEngine gracefully
#3104 opened Jan 30, 2025 by AvisP
@grimoire
3
[Bug] gradio does not recognize URLs and local paths properly
#3102 opened Jan 29, 2025 by Lychee-acaca
3 tasks done
@irexyc
1
[Bug] CUDA error with Qwen/Qwen2-VL-7B-Instruct
#3101 opened Jan 29, 2025 by andoorve
3 tasks done
1
[Bug] LogitsWarper deprecated in transformers? (trying to run Qwen/Qwen2.5-VL-72B-Instruct)
#3100 opened Jan 29, 2025 by josephrocca
3
[Feature] 建议官方在kaggle上使用lmdeploy完整安装资源开放一个公共笔记本用来展示lmdeploy的推理性能
#3098 opened Jan 29, 2025 by xiezhipeng-git
@lvhan028
6
[Feature] Set cache_dir like the one used in AutoModel in HuggingFace transformers awaiting response
#3096 opened Jan 27, 2025 by Yuco-Z
3
[Feature] Automatically Free pipeline of Prompts
#3095 opened Jan 27, 2025 by richardjonker2000
1
[Feature] Support for sparse attention
#3093 opened Jan 27, 2025 by youyc22
[Bug] tp>1时，进行多视频batch推理没有结果输出
#3092 opened Jan 26, 2025 by qingchunlizhi
3 tasks done
[Bug] 如何在指定卡上加载lmdeploy加速的模型
#3091 opened Jan 26, 2025 by qingchunlizhi
3 tasks done
Do LoRA adapters support the vision encoder?
#3090 opened Jan 25, 2025 by pbarker
[Feature] Add support for SmolVLM multimodal models
#3089 opened Jan 25, 2025 by thisiskofi
华为Ascend 310P卡是否支持部署qwen2.5-72B ?
#3082 opened Jan 24, 2025 by kelvennn
@jinminxi104
[BUG] 通过lmdeploy推理sft后qwen2-vl模型，特定数据偶发报错
#3078 opened Jan 23, 2025 by boceng
3 tasks done
@RunningLeon
2
[Bug] The program on the main graphics card gets stuck when running with multiple graphics cards.
#3071 opened Jan 22, 2025 by LKELN
3 tasks done
@lvhan028
1
[Bug] bad performance on model Molmo-7B-D-0924
#3066 opened Jan 21, 2025 by zhulinJulia24
3 tasks
@lvhan028
[Bug] turbomind has not been built with fp32 support
#3065 opened Jan 21, 2025 by syorami
2 of 3 tasks
@lvhan028
4
model transfer to Turbomind cost a lot of time.
#3064 opened Jan 21, 2025 by LaoWangGB
@lvhan028
8
[Bug] LMDeploy v0.6.4-cu12使用2张4090无法启动和推理, v0.6.0-cu12 可以正常启动和推理
#3062 opened Jan 21, 2025 by simonwei97
3 tasks done
@irexyc
1
[Feature] lora can batch inference in lmdeploy?
#3060 opened Jan 21, 2025 by MichoChan
@RunningLeon
1
[Bug] 多轮对话历史中如果包含tool_calls，则response中的tool_calls arguments会被额外嵌套一层string
#3058 opened Jan 21, 2025 by ExenVitor
3 tasks done
@AllentDan
7
Stuck during parallel inference.
#3057 opened Jan 20, 2025 by Lanbai-eleven
@lzhangzz
9
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.