-
Notifications
You must be signed in to change notification settings - Fork 406
Issues: InternLM/lmdeploy
[Benchmark] benchmarks on different cuda architecture with mo...
#815
opened Dec 11, 2023 by
lvhan028
Open
9
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[Bug] no user input makes api server throw exception with MLLM
#2658
opened Oct 25, 2024 by
gaord
3 tasks
[Feature] how to get the token score(logprob) of greedy decoder?
#2652
opened Oct 24, 2024 by
Wondersui
[Bug] use new 4bits quantizated models of internlm2, decoded word starts with a blank.
#2651
opened Oct 24, 2024 by
zhulinJulia24
3 tasks
[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
[Bug] Phi-3-vision-128k-instruct 跑模型在8卡上出现 “Expected all tensors to be on the same device, but found at least two devices”
mllm
#2633
opened Oct 22, 2024 by
dreamerlin
3 tasks done
[Bug] qwen2-vl-7b docker delpoy bugs
awaiting response
#2629
opened Oct 22, 2024 by
jnzbfgjd
3 tasks done
[Feature] Combine Batched Inference and Chat Conversation in VLMs Deployment
#2628
opened Oct 21, 2024 by
Yusepp
[Bug] When TP = 4 and prefix cache is enabled, no result is generated.
#2611
opened Oct 17, 2024 by
rbao2018
3 tasks done
[Bug] InternVL2-26B model load extremely slow
#2608
opened Oct 16, 2024 by
HappyNotHappy
3 tasks done
使用xtuner chat 和 lmdeploy chat 调用未量化的模型,一直生成答案而不停止
awaiting response
Stale
#2597
opened Oct 13, 2024 by
liguoyu666
[Bug] pipeline如何指定显卡进行推理,例如我想使用cuda:1进行推理,目前文档还没发现如何设置
awaiting response
#2592
opened Oct 12, 2024 by
aizhweiwei
3 tasks
[Bug] Qwen/Qwen2-VL-7B-Instruct 用--tp 2直接弹出Docker了,不用--tp运行正常。
awaiting response
#2590
opened Oct 11, 2024 by
wangaocheng
3 tasks done
v1/chat/interactive方式调用lmdeploy,interactive_mode=true, 图片刷新,问题不变,回答结果永远一样,这是什么原因导致的呢?
#2589
opened Oct 11, 2024 by
zhoulin2545210131
3 tasks done
Previous Next
ProTip!
What’s not been updated in a month: updated:<2024-09-26.