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

287 Open 1,170 Closed
287 Open 1,170 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

[Docs] LoRA 推理服务
#2686 opened Oct 31, 2024 by LIUKAI0815
@AllentDan
1
[Feature] Whether pytorch backend is supported on Windows?
#2684 opened Oct 30, 2024 by eeyrw
1
[Bug] min_p from request is not used
#2682 opened Oct 29, 2024 by ErykCh
2 of 3 tasks
@AllentDan
1
mllama3.2-V-11b support text-only mode?
#2680 opened Oct 29, 2024 by AnyangAngus
@AllentDan
5
[Bug] pytorch backend 's precision points loss 1.0-2.5 points between main code and v0.6.1 on some models.
#2679 opened Oct 29, 2024 by zhulinJulia24
3 tasks
@grimoire
[Feature] Support QwenVL on Ascend
#2675 opened Oct 29, 2024 by Yang1032
@jinminxi104
[Feature] support multi-lora in turbomind backend
#2674 opened Oct 28, 2024 by zzf2grx
[Feature] Response Metrics
#2673 opened Oct 28, 2024 by nathan-az
@AllentDan
2
[Bug] no user input makes api server throw exception with MLLM
#2658 opened Oct 25, 2024 by gaord
3 tasks
@irexyc
1
[Bug] use new 4bits quantizated models of internlm2, decoded word starts with a blank.
#2651 opened Oct 24, 2024 by zhulinJulia24
3 tasks
@AllentDan
[Bug] AWQ量化InternVL2 20B输出无意义的杂乱文本
#2650 opened Oct 24, 2024 by diandianliu
1 of 3 tasks
@AllentDan
11
[Bug] Use triton to deploy minicpm-v-2_6 GPU memory keeps increasing until it overflows
#2642 opened Oct 24, 2024 by LinJianping
1 of 3 tasks
@RunningLeon
1
[Feature] Metrics Endpoint
#2638 opened Oct 23, 2024 by eldhosemjoy
@AllentDan
1
[Bug] cpu 100%
#2637 opened Oct 23, 2024 by whk6688
3 tasks
@AllentDan
1
[Bug] Phi-3-vision-128k-instruct 跑模型在8卡上出现 “Expected all tensors to be on the same device, but found at least two devices” mllm
#2633 opened Oct 22, 2024 by dreamerlin
3 tasks done
@RunningLeon
4
[Bug] qwen2-vl-7b docker delpoy bugs awaiting response
#2629 opened Oct 22, 2024 by jnzbfgjd
3 tasks done
@lvhan028
1
[Feature] Combine Batched Inference and Chat Conversation in VLMs Deployment
#2628 opened Oct 21, 2024 by Yusepp
[Bug] 对InternVL模型进行推理时，图像编码阶段gpu-cpu的传输时间过长
#2624 opened Oct 19, 2024 by Dimensionzw
3 tasks done
@irexyc
2
[Bug] qwen2-vl-72b无法使用
#2622 opened Oct 18, 2024 by bltcn
3 tasks done
@grimoire
2
[Bug] Internvl2-8B模型量化后推理速度减慢
#2616 opened Oct 18, 2024 by guozhiyao
3 tasks
2
[Bug] When TP = 4 and prefix cache is enabled, no result is generated.
#2611 opened Oct 17, 2024 by rbao2018
3 tasks done
@lvhan028
1
[Feature] qwen2.5 是否可以支持tool_calls传入？ awaiting response
#2610 opened Oct 17, 2024 by akai-shuuichi
2
internvl2量化是否支持自定义calib-dataset？
#2609 opened Oct 16, 2024 by guozhiyao
@AllentDan
1
[Bug] InternVL2-26B model load extremely slow
#2608 opened Oct 16, 2024 by HappyNotHappy
3 tasks done
[Bug] InternVL2-2B的推理速度慢，发现是视觉特征提取的耗时很长
#2604 opened Oct 15, 2024 by fong-git
3 tasks
@irexyc
10
ProTip! Find all open issues with in progress development work with linked:pr.