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

270 Open 1,089 Closed
270 Open 1,089 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

关于internvl4B模型完全没有加速，甚至更慢的问题
#2486 opened Sep 19, 2024 by daihuidai
@grimoire
4
[Feature] Qwen2.5系列能支持一下吗？
#2481 opened Sep 19, 2024 by tiaotiaosong
@AllentDan
2
[Bug]TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]
#2476 opened Sep 18, 2024 by LIUKAI0815
3 tasks
1
[Bug] The parameters n=number_outputs does not work in the function: response = client.chat.completions.create awaiting response
#2474 opened Sep 17, 2024 by leoozy
3 tasks done
1
Ascend NPU support awaiting response
#2471 opened Sep 15, 2024 by zer0py2c
3
[Bug/Feature] Keep-alive \n should be sent roughly every 30 seconds in Event Stream responses to prevent connection timeout errors for cases of very long ITL
#2470 opened Sep 14, 2024 by josephrocca
@AllentDan
4
[Bug] 2x4090 with Llama2 70B silently crashes (i.e. without any error message in DEBUG mode) as of v0.6.0a0 and v0.6.0 (but works fine in previous versions)
#2468 opened Sep 14, 2024 by josephrocca
3 tasks done
@irexyc
10
[Feature] How to use awq with my own dataset
#2463 opened Sep 13, 2024 by wangzhongren-code
@AllentDan
[Feature] support s-lora in turbomind backend
#2458 opened Sep 12, 2024 by torinchen
2
[Bug] output not consistent with different max_prefill_token_num for long context input on pytorch engine
#2457 opened Sep 12, 2024 by RunningLeon
3 tasks done
@grimoire
InternVL2在做AWQ量化的时候，不能支持自定义的校准数据集吗 awaiting response
#2456 opened Sep 12, 2024 by tanguozhu
@AllentDan
4
MiniCPM3-4B会支持吗？
#2455 opened Sep 12, 2024 by LIUKAI0815
@AllentDan
1
[Bug] triton.runtime.autotuner.OutOfResources: out of resource: shared memory, Required: 108672, Hardware limit: 101376. Reducing block sizes or num_stages may help.
#2451 opened Sep 12, 2024 by EvoNexusX
3 tasks done
@grimoire
3
[Bug] LongCite-glm4-9b awq quantization error
#2450 opened Sep 11, 2024 by maxin9966
3 tasks
@AllentDan
1
[Feature] pipe如何输出scores awaiting response
#2448 opened Sep 11, 2024 by KooSung
@irexyc
1
[Bug] CUDA runtime error when running Llama-3.1-70B-Instruct-AWQ-INT4 awaiting response
#2442 opened Sep 10, 2024 by rtadewald
1 of 3 tasks
@lvhan028
3
[Bug] lmdeploy does not support the regularized lora target module awaiting response
#2439 opened Sep 10, 2024 by orzgugu
2 of 3 tasks
@irexyc
1
[Bug] 请问一下，我用qwen2的模型，仿照internlm-xcomposer2中的plora方式训练了一个VL模型，这个模型应该怎样用lmdeploy部署起来 awaiting response
#2437 opened Sep 10, 2024 by alanayu
3 tasks
@irexyc
2
[Feature] 能否支持一下qwenvl2 awaiting response
#2436 opened Sep 9, 2024 by Ranking666
@irexyc
3
是否支持embedding模型部署
#2432 opened Sep 6, 2024 by Toblame
1
[Bug] cogvlm2支持的问题 awaiting response
#2430 opened Sep 6, 2024 by tdf1995
1 of 3 tasks
@RunningLeon
1
[Bug] 部署internvl2自己lora微调的模型，显存占用非常高，快速爬升到了60g正常吗
#2425 opened Sep 5, 2024 by yywangfei
1 of 3 tasks
1
[Feature] Profiling GeMM kernel in lmdeploy
#2424 opened Sep 4, 2024 by DerrickYLJ
@lzhangzz
1
[Feature] when --tp 2 awaiting response
#2423 opened Sep 4, 2024 by maxin9966
@lvhan028
6
[Docs] AWQ / GPTQ 部分
#2422 opened Sep 4, 2024 by Skyseaee
@AllentDan
1
ProTip! Mix and match filters to narrow down what you’re looking for.