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

219 Open 883 Closed
219 Open 883 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] Can't Quantize llava-v1.6-34b (AssertionError)
#2079 opened Jul 18, 2024 by rtadewald
2 tasks done
输出全是乱码[Bug]
#2078 opened Jul 18, 2024 by quanfeifan
2 tasks
The offline inference speed of lmdeploy is very slow
#2077 opened Jul 18, 2024 by zhaopings
2 tasks
[Feature] Cannot find a way to disable custom_all_reduce: getting "[TM][WARNING] Device 0 peer access Device 1 is not available." messages
#2076 opened Jul 18, 2024 by Subarasheese
[Bug] Sending image from gradio interface to 4bit model
#2075 opened Jul 18, 2024 by zhuraromdev
2 tasks
1
[Bug] Seems not to support Qwen-VL-Chat?
#2074 opened Jul 18, 2024 by TayeeChang
2 tasks done
[Bug] lmdeploy Auto AWQ量化后的4bit模型生成内容全部为"姿势姿势...."
#2073 opened Jul 18, 2024 by MingyuZha
2 tasks done
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
#2072 opened Jul 18, 2024 by sunzx8
[Feature] api server部署方式下的logprob功能
#2070 opened Jul 18, 2024 by cjfcsjt
1
[Bug] 使用lmdeploy部署InternVL2-2B-AWQ 无法正常回复
#2069 opened Jul 18, 2024 by blackblue9
1 of 2 tasks
9
[Bug] Internvl2-llama3-76B 在8卡V100上报错不支持 flash attention awaiting response v100 v100 related issue
#2067 opened Jul 18, 2024 by thesby
2 tasks done
7
[Bug] The problem of very low multi-card inference efficiency
#2066 opened Jul 17, 2024 by maxin9966
2 tasks
1
[Feature] 请支持离线pipeline推理显存清空的功能
#2064 opened Jul 17, 2024 by Davidgzx
[Bug] 使用官方镜像v0.5.1进行GLM4v的部署会有一个报错
#2060 opened Jul 17, 2024 by ZhiyuYUE
2 tasks
@RunningLeon
3
[Bug]MiniCPM-V 2.0是没有支持吗？
#2058 opened Jul 17, 2024 by DankoZhang
2 tasks done
4
想问下Lmdeploy支持base model加多lora的部署方式么 awaiting response
#2057 opened Jul 17, 2024 by will-wiki
2
[Bug] 最新版 lmdeploy 0.5.1 在v100以及rtx 2080 ti 上部署cogvlm2，推理过程会报错： ERROR - Engine loop failed with error: map::at v100 v100 related issue
#2055 opened Jul 17, 2024 by kklots
2 tasks done
@RunningLeon
8
Memory leak
#2054 opened Jul 17, 2024 by xiaoxiangshusheng
2
Florence 2 support :)
#2052 opened Jul 16, 2024 by SinanAkkoyun
1
[Bug] Segmentation fault during run of quantized internlm/internlm-xcomposer2-4khd-7b model
#2051 opened Jul 16, 2024 by zhuraromdev
2 tasks
1
[Bug] 无法使用双卡的显存来共同加载一个模型 awaiting response
#2049 opened Jul 16, 2024 by keakon
2 tasks done
8
使用pipline进行批量推理报错[Bug]
#2047 opened Jul 16, 2024 by hitzhu
2 tasks done
4
[Feature] 目前TurboMind engine 不支持lora吗，后续会支持吗
#2045 opened Jul 16, 2024 by wongyan-data
3
[Bug] gradio reset button stucked after I cancel a response.
#2043 opened Jul 16, 2024 by zhulinJulia24
2 tasks
@AllentDan
[Feature] Support logprob in VLM api server
#2041 opened Jul 16, 2024 by cjfcsjt
1
ProTip! Add no:assignee to see everything that’s not assigned.