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

274 Open 1,120 Closed
274 Open 1,120 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] Providing tool response back to llm for output generation is broken for llama3.1 8B
#2542 opened Sep 30, 2024 by S1LV3RJ1NX
3 tasks done
[Feature] 请支持molmo视觉大模型
#2541 opened Sep 30, 2024 by win4r
[Bug] 升级0.6.1之后 proxy 的 api-keys 参数不支持逗号分隔的list了
#2537 opened Sep 30, 2024 by snachx
3 tasks done
启用prefix_cache时，同分辨率图片会缓存命中情况下如何推理时区分
#2536 opened Sep 30, 2024 by zhuchen1109
[Bug] 910b multi-card reasoning is very slow.
#2534 opened Sep 29, 2024 by the-nine-nation
3 tasks done
@jinminxi104
1
[Bug] NPU是否支持glm4v-9b的部署推理
#2533 opened Sep 29, 2024 by Sunxiaohu0406
3 tasks
1
[Feature] 对比vllm推理速度
#2532 opened Sep 29, 2024 by senlice
[Bug] v0.6.1 Qwen2-VL-7B
#2531 opened Sep 29, 2024 by smallflyingpig
3 tasks
1
关于运行时候时间差异过大的问题
#2529 opened Sep 28, 2024 by lwdnxu
[Bug] lmdeploy + InternVL2-40B-AWQ hangs under a certain number of asynchronous requests
#2528 opened Sep 27, 2024 by hkunzhe
3 tasks done
@irexyc
4
[Feature] Please support Llama3.2 and Qwen2.5
#2526 opened Sep 27, 2024 by mihara-bot
4
[Feature] InternVL2-4B turbomind支持
#2524 opened Sep 27, 2024 by AIFFFENG
[Bug] error when serving glm4-9b-chat-1m
#2522 opened Sep 26, 2024 by YanShuang17
3 tasks
1
[Feature] Support Llama 3.2 family of models
#2517 opened Sep 26, 2024 by vikrantrathore
@AllentDan
1
[Bug] llama3.1 70B v1/chat/completions error on Huawei Ascend 910B
#2515 opened Sep 25, 2024 by nullxjx
2 of 3 tasks
@jinminxi104
4
[Bug] internlm2_5-7b-chat多卡部署报错 aborted
#2508 opened Sep 24, 2024 by SachaHu
2 of 3 tasks
3
[Feature] Any way to get the logits instead of logprobs in lmdeploy?
#2507 opened Sep 24, 2024 by hmzo
@irexyc
2
[Feature] Qwen-VL-72B-Instruct awaiting response
#2503 opened Sep 24, 2024 by yeonggon
1
[Feature] Hope the pipeline can automatically destroy resources
#2498 opened Sep 23, 2024 by Volta-lemon
@irexyc
[Feature] Will multi-modal models support W8A8 quantization in the future?
#2496 opened Sep 23, 2024 by MenglingD
@AllentDan
6
可以支持加载本地lora路径吗 awaiting response
#2495 opened Sep 23, 2024 by LIUKAI0815
@grimoire
2
[Feature] 未来会支持gptq-int3模型吗？ awaiting response Stale
#2492 opened Sep 22, 2024 by maxin9966
4
[Feature] internvl2+lmdeploy部署推理视频，有没有控制采样频率，前处理的参数？目前的推理时间过长了 awaiting response
#2489 opened Sep 20, 2024 by PancakeAwesome
1
关于internvl4B模型完全没有加速，甚至更慢的问题 awaiting response
#2486 opened Sep 19, 2024 by daihuidai
@grimoire
8
[Bug]TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]] awaiting response
#2476 opened Sep 18, 2024 by LIUKAI0815
3 tasks
4
ProTip! Follow long discussions with comments:>50.