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

302 Open 1,219 Closed
302 Open 1,219 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] Lmdeploy推理InternVL2系列是否支持在输入图片层级(假设输入多图)设定max_num以及use_thumbnali的超参
#2824 opened Nov 27, 2024 by laserwave
@irexyc
1
[Bug] 4-bit KV cache results in very low performance while 8-bit KV cache is almost lossless
#2822 opened Nov 26, 2024 by fzyzcjy
3 tasks done
[Feature] 想尝试将cogvideox的模型转成lmdeploy，请问这操作可能实现吗？
#2821 opened Nov 26, 2024 by DamonsJ
[Bug] glm-4v-9b在昇腾卡推理报错
#2819 opened Nov 26, 2024 by Sunxiaohu0406
3 tasks
[Bug] ImportError: cannot import name 'AWQ_INSTALLED' from 'awq.modules.linear.gemm' (D:\Programs\conda_envs\lmdeploy2\lib\site-packages\awq\modules\linear\gemm.py)
#2816 opened Nov 26, 2024 by Zhangwt95
3 tasks
[Feature] 怎么通过python代码直接获取命中的prefix前缀长度，而不进行推理等计算
#2808 opened Nov 25, 2024 by diggle001
有计划支持Marco-o1吗？
#2807 opened Nov 25, 2024 by qiuxuezhe123
3 tasks
[Bug] docker+lmdeploy deploys multimodal large model and reports an error：AssertionError: failed to match chat template, please explicit set chat_template_config（docker+lmdeploy部署多模态大模型）
#2805 opened Nov 25, 2024 by Aanlifire
3 tasks done
@irexyc
1
[Bug] Why the example/cpp/llama/llama_triton_example.cc does not call the LlamaTritonModel::createEngine()?
#2803 opened Nov 25, 2024 by BigFaceBoy
3 tasks done
@lzhangzz
[Bug] Logprobs always NULL
#2802 opened Nov 25, 2024 by BrennanCode1
3 tasks done
@irexyc
How to disable chat templates in lmdeploy vlm ?
#2800 opened Nov 25, 2024 by sleepwalker2017
@irexyc
[Feature] 可以考虑支持THUDM/cogvlm2-llama3-chinese-chat-19B-int4模型吗
#2799 opened Nov 24, 2024 by Jerryporter
@AllentDan
1
[Bug] Does PytorchEngine Visual Model Support Prefix Caching?
#2789 opened Nov 21, 2024 by OftenDream
3 tasks
@grimoire
1
[Bug] Llama-3.2-1B-Instruct and InternVL2-1B does not supported kvin4, is that expected?
#2786 opened Nov 21, 2024 by zhulinJulia24
3 tasks
@lzhangzz
2
[Bug] Response of converted Qwen2-57B-A14B-Instruct-GPTQ-Int4 returns garbled characters
#2785 opened Nov 21, 2024 by zhulinJulia24
3 tasks
@lvhan028
1
[Bug] SystemExit: 1 asyncio.exceptions.TimeoutError
#2782 opened Nov 20, 2024 by LIUKAI0815
2 of 3 tasks
@AllentDan
15
[Bug] Qwen2.5无法跑通tools call(官方案例代码) awaiting response
#2775 opened Nov 20, 2024 by turkeymz
3 tasks done
2
[Feature] qwen2 vl support the turbomind engine
#2774 opened Nov 20, 2024 by DexterGuo
@irexyc
2
[Feature] turbomind后端是否会支持guided_decoding
#2771 opened Nov 19, 2024 by shell-nlp
@lvhan028
3
[Bug] The quantization process of Qwen/Qwen2-VL-7B-Instruct is getting killed without throwing error.
#2770 opened Nov 19, 2024 by vjaideep08
3 tasks done
@AllentDan
2
[Bug] 昇腾910B通过lmdeploy镜像，使用qwen2-vl-7b模型，推理过程报错： call aclnnBatchMatMul failed
#2769 opened Nov 18, 2024 by fusmile0101
1 of 3 tasks
@jinminxi104
How can I specify the rope scaling type when starting the API server?
#2768 opened Nov 18, 2024 by snachx
@lvhan028
1
[Feature] W4A8-FP8 support in AWQ quantization
#2766 opened Nov 18, 2024 by yongchaoding
@lzhangzz
2
[Bug] lmdeploy加载lora微调模型报错
#2762 opened Nov 17, 2024 by ltt-gddxz
3 tasks done
@RunningLeon
4
[Bug] The script "profile_generation.py" went haywire and crashed
#2760 opened Nov 15, 2024 by yuchiwang
3 tasks done
@jinminxi104
1
ProTip! Mix and match filters to narrow down what you’re looking for.