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

290 Open 1,199 Closed
290 Open 1,199 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

[Feature] Support response_format for TurboMind
#2753 opened Nov 13, 2024 by h4n0
[Bug] 0.6.2 vs 0.4.2 qwen1.5b模型，0.6.2推理性能差距有慢3倍
#2752 opened Nov 13, 2024 by xliangwu
1 of 3 tasks
@lvhan028
4
[Feature] 请问function calling是否只适配本项目的后端servcer awaiting response
#2747 opened Nov 13, 2024 by positive666
@AllentDan
1
[Feature] 有昇腾平台的模型性能测试数据吗
#2746 opened Nov 13, 2024 by zainlau
@jinminxi104
1
[Bug] Cannot install torch-npu==2.3.1, torch==2.3.1 and torchvision==0.18.1 because these package versions have conflicting dependencies.
#2745 opened Nov 13, 2024 by jiabao-wang
3 tasks
@CyCle1024 @jinminxi104
2
[Bug] 似乎卡死的都是VLM模型，看着是个系统性问题？
#2743 opened Nov 13, 2024 by DefTruth
3 tasks
@irexyc
1
[Feature] Qwen2-VL支持video
#2735 opened Nov 11, 2024 by evi-Genius
[Feature] The cache-max-entry-count working off percentages makes it difficult to setup multiple servers awaiting response
#2732 opened Nov 9, 2024 by mrakgr
@lvhan028
3
[Bug] Accuracy of W8A8 is big different from that of the original model
#2730 opened Nov 9, 2024 by HelloCard
3 tasks done
@AllentDan
6
[Bug] How to improve the first frame response speed TTFT awaiting response
#2728 opened Nov 8, 2024 by zhouyuustc
3 tasks done
1
[Bug] Deployment of Llama3.1-70b getting struck
#2724 opened Nov 7, 2024 by pulkitmehtaworkmetacube
3 tasks done
@lvhan028
7
lmdeploy - ERROR - __init__.py:17 - ModuleNotFoundError: No module named 'dlinfer' awaiting response
#2722 opened Nov 7, 2024 by jiabao-wang
3 tasks
@jinminxi104
1
[Bug] 显存溢出后程序卡死，而不是报错
#2712 opened Nov 5, 2024 by Weiyun1025
3 tasks
@irexyc
1
[Bug] 并发场景下，发起大的输入token请求时会导致流式响应出现问题 awaiting response
#2709 opened Nov 5, 2024 by zhouyuustc
3 tasks done
1
[Bug] InternVL2-1B performance of lmdeploy is much worse compared to the original Hugging Face PyTorch model.
#2705 opened Nov 4, 2024 by henry16lin
3 tasks done
@RunningLeon
7
[Bug] CUDA 12.5 源码编译 test_utils.cu 报错
#2702 opened Nov 4, 2024 by DefTruth
3 tasks
@lzhangzz
1
api_server 方式部署有概率卡住 awaiting response
#2691 opened Oct 31, 2024 by LiYtao
1 of 3 tasks
@lzhangzz
3
[Docs] LoRA 推理服务
#2686 opened Oct 31, 2024 by LIUKAI0815
@AllentDan
1
[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
@lvhan028
[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] 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
3
ProTip! Mix and match filters to narrow down what you’re looking for.