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

335 Open 1,297 Closed
335 Open 1,297 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] deepseek v3 deployment on h200
#3049 opened Jan 18, 2025 by zhyncs
3 tasks
@grimoire
2
[Bug] gemma2 model reports an error when doing evaluation
#3048 opened Jan 17, 2025 by zhulinJulia24
3 tasks
@AllentDan
turbomind 支持结构化输出
#3047 opened Jan 17, 2025 by ZanePoe
1
[Feature] Relax peft version
#3046 opened Jan 16, 2025 by Galaxy-Husky
@RunningLeon
1
Is there a convenient way to perform model conversion? awaiting response
#3043 opened Jan 16, 2025 by Lanbai-eleven
@lvhan028
3
[Feature] support for deepseek-vl2
#3042 opened Jan 16, 2025 by gystar
@CUHKSZzxy
以服务方式部署VLM，如何上传本地图片？ awaiting response
#3040 opened Jan 16, 2025 by yimuu
@lvhan028
1
[Bug] history tokens is not correct with /v1/chat/interactive.
#3032 opened Jan 15, 2025 by zhulinJulia24
3 tasks
@lzhangzz
1
[Bug] Tokenizer Parallelism Leads to (500 : Internal Server Error)
#3025 opened Jan 14, 2025 by Mr-Loevan
3 tasks done
1
[Bug] The output cannot stop and there are a lot of repetitions on OpenGVLab/Mini-InternVL-Chat-2B-V1-5-inner-4bits and OpenGVLab/InternVL2-1B
#3022 opened Jan 14, 2025 by zhulinJulia24
3 tasks
@lzhangzz
Is there a way to limit max concurrent requests?
#3019 opened Jan 13, 2025 by heibaidaolx123
@AllentDan
1
在H100上使用pytorch backend推理报错<Triton> check failed
#3017 opened Jan 13, 2025 by sunxiaoyu12
@RunningLeon
4
[Bug] It seems the second round of answers lost the context of the first round in baichun2-13b-chat models with pytorch backend or CodeLlama-7b-Instruct-hf with turbomind backend
#3015 opened Jan 13, 2025 by zhulinJulia24
3 tasks
[Bug] 请问在T4上进行qwen2-14B awq4版模型推理耗时远远大于相同模型在vllm上推理的耗时，是参数哪里有问题吗？相同配置在A800上性能确实能提升
#3012 opened Jan 12, 2025 by sundayKK
3 tasks
[Bug] OOM in jetson but not in x86
#3006 opened Jan 9, 2025 by quanfeifan
3 tasks
@lzhangzz
3
[Bug] CUDA error: an illegal memory access was encountered. Vicuna results wrong
#3004 opened Jan 9, 2025 by AllentDan
3 tasks
@grimoire
[Bug] 使用lmdeploy0.6.4部署llava-hf/llava-v1.6-vicuna-13b-hf之后，openai调用输出为空字符串
#3003 opened Jan 9, 2025 by bang123-box
3 tasks
@lvhan028
[Bug] RuntimeError: Triton Error [CUDA]: an illegal memory access was encountered awaiting response
#2999 opened Jan 8, 2025 by YSShannon
1 of 3 tasks
@RunningLeon
5
[Bug] internvl2_8b, 4 3090 cards, CUDA OOM error
#2993 opened Jan 7, 2025 by zhaowenZhou
3 tasks done
@irexyc
1
[Bug] 随着时间运行，lmdeploy进程占用cpu提高且不释放
#2990 opened Jan 6, 2025 by akai-shuuichi
3 tasks done
@AllentDan
5
昇腾lmdeploy使用 lmdeploy APIClient 接口时，推理结果被截断
#2969 opened Dec 28, 2024 by winni0
3 tasks done
@jinminxi104
5
[Feature] W8A8 support for turbomind engine
#2962 opened Dec 27, 2024 by binhtranmcs
1
[Docs] inference DeepSeek-V3 with LMDeploy
#2960 opened Dec 26, 2024 by haswelliris
14
[Feature] Support Medusa decode (Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads)
#2950 opened Dec 25, 2024 by yimuu
[Bug] generation profile hangs on Mixtral-8x7B-Instruct-v0.1 with pytorch backend
#2948 opened Dec 24, 2024 by zhulinJulia24
3 tasks
1
@grimoire
2
ProTip! Mix and match filters to narrow down what you’re looking for.