Skip to content

Issues: InternLM/lmdeploy

Beta
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

420 Open 1,453 Closed
420 Open 1,453 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] Qwen3的enable_thinking参数目前不支持
#3511 opened Apr 30, 2025 by nemo326
3 tasks
1
[Feature] 支持Skywork/Skywork-R1V2-38B模型
#3509 opened Apr 30, 2025 by ZanePoe
[Feature] 是否支持部署Qwen3-235B-A22B Q4量化版本
#3507 opened Apr 30, 2025 by yangpeng-space
[Feature] 是否支持在ascend 310p上部署internvl3
#3502 opened Apr 29, 2025 by David1-git
@jinminxi104
qwen2_5-7b model --- quantization awaiting response
#3501 opened Apr 29, 2025 by cnzyr
5
[Feature] Add Support to Video Generation Models and architectures backlog
#3497 opened Apr 28, 2025 by KaifAhmad1
1
[Feature] 视觉大模型中视觉部分通过tensorrt
#3485 opened Apr 27, 2025 by fighterzzzh
1
310P是否支持qwen2.5-vl
#3483 opened Apr 25, 2025 by Huang-zhenxuan
@jinminxi104
1
[Bug] A100单卡40G执行lmdeploy报错Aborted (core dumped)
#3473 opened Apr 23, 2025 by yufanghui
3 tasks done
elegant way to set max-pixels of Qwen2.5-VL awaiting response
#3472 opened Apr 23, 2025 by Li-Jicheng
1
[Feature] 指定gpu
#3464 opened Apr 21, 2025 by AUTOMATIC2222
ERROR - engine.py:781 - Task <EngineMainLoop> failed
#3459 opened Apr 21, 2025 by KDD2018
@CUHKSZzxy
2
[Bug] Object creation will fail if spilling is required.
#3457 opened Apr 21, 2025 by github-eliviate
1 of 3 tasks
2
[Docs] how to get the prefill hidden states?
#3456 opened Apr 20, 2025 by haowen-han
[Bug]
#3453 opened Apr 18, 2025 by waveman800
2 of 3 tasks
1
[Bug] 更改session_len无法解决输出截断的问题
#3451 opened Apr 17, 2025 by Amber-Believe
2 of 3 tasks
@CUHKSZzxy
2
[Bug] Deepseek-V2 MOE 模型加载适配问题
#3449 opened Apr 17, 2025 by Skyseaee
3 tasks done
@irexyc
1
[Bug]部署Phi-4-mini-instruct，调用的时候报错 awaiting response
#3447 opened Apr 17, 2025 by LIUKAI0815
3 tasks done
@RunningLeon
2
[Bug]对VLM来说，是否支持多个lora adapter使用
#3444 opened Apr 17, 2025 by Amber-Believe
1 of 3 tasks
@grimoire
5
模型权重加载很慢（qwenvl 2.5 和 internvl 2.5） awaiting response
#3438 opened Apr 16, 2025 by ccccwb
@RunningLeon
4
[Bug] MiniCPM-V-2_6 and InternVL2_5-26B are not supported when communicator='native'. Is that expected?
#3434 opened Apr 15, 2025 by zhulinJulia24
3 tasks
@lvhan028
[Bug] QwQ-32B error: argument tool-call-parser: not allowed with argument--reasoning-parser
#3431 opened Apr 14, 2025 by jingyibo123
3 tasks done
@RunningLeon
[Bug] 推DeepCoder-14B中间报错
#3428 opened Apr 14, 2025 by cyber-tao
3 tasks done
@irexyc
3
Is lmdeploy now support Qwen2.5-Omni-7B? backlog
#3427 opened Apr 14, 2025 by LiSherman
1
[Bug] qwen2.5-vl-7b用lmdeploy框架部署后输出结果与原生模型不一致 awaiting response
#3422 opened Apr 11, 2025 by hcguoO0
3 tasks
@CUHKSZzxy
6
ProTip! Add no:assignee to see everything that’s not assigned.