-
Notifications
You must be signed in to change notification settings - Fork 390
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] 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
[Bug] 910b multi-card reasoning is very slow.
#2534
opened Sep 29, 2024 by
the-nine-nation
3 tasks done
[Bug] lmdeploy + InternVL2-40B-AWQ hangs under a certain number of asynchronous requests
#2528
opened Sep 27, 2024 by
hkunzhe
3 tasks done
[Bug] llama3.1 70B v1/chat/completions error on Huawei Ascend 910B
#2515
opened Sep 25, 2024 by
nullxjx
2 of 3 tasks
[Feature] Any way to get the logits instead of logprobs in lmdeploy?
#2507
opened Sep 24, 2024 by
hmzo
[Feature] Hope the pipeline can automatically destroy resources
#2498
opened Sep 23, 2024 by
Volta-lemon
[Feature] Will multi-modal models support W8A8 quantization in the future?
#2496
opened Sep 23, 2024 by
MenglingD
[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
[Bug]TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]
awaiting response
#2476
opened Sep 18, 2024 by
LIUKAI0815
3 tasks
Previous Next
ProTip!
Follow long discussions with comments:>50.