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

366 Open 1,378 Closed
366 Open 1,378 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] NPU下Qwen2.5-VL推理报错
#3237 opened Mar 10, 2025 by tcye
3 tasks done
[Bug] 批量推理时显示eos stop_words_list 长度超限，最后(core dumped)
#3233 opened Mar 8, 2025 by Kismeu
1 of 3 tasks
@irexyc
1
Support for Flash Attention 3 for Ampere, Ada, and Hopper in LMDeploy
#3232 opened Mar 8, 2025 by radna0
@lzhangzz
[Bug] 使用profile_restful_api.py测试api_server时出现若干bug
#3231 opened Mar 8, 2025 by cccccya
3 tasks
@grimoire
1
[Bug] 使用lmdeploy serve proxy 分发服务管理下游服务，导致stream模式丢失
#3227 opened Mar 7, 2025 by Gierry
3 tasks
@AllentDan
3
VLM的serve支持请求分发/负载均衡吗？
#3226 opened Mar 7, 2025 by yaogang2060
@AllentDan
7
[Bug]使用wsl的Ubuntu22.04系统，lmdeploy任何版本使用pytorch引擎部署，加载权重文件非常卡，单个权重文件(144s/it),32B-AWQ启动 一次需要10分钟
#3225 opened Mar 6, 2025 by Gierry
3 tasks done
@grimoire
7
[Bug] no chat-template for QwQ 32B AWQ
#3224 opened Mar 6, 2025 by HuChundong
3 tasks
@AllentDan
4
lmdeploy + batch inference是推理加速的极限吗？
#3222 opened Mar 6, 2025 by nzomi
[Bug] libharpcuda.so.0: cannot open shared object file: No such file or directory
#3211 opened Mar 4, 2025 by 3mpt
3 tasks
@RunningLeon
1
[Bug]在910B上量化后部署好无法正常访问
#3201 opened Mar 3, 2025 by jxz542189
3 tasks done
@jinminxi104
1
[HELP] 求好心人帮忙量化 DeepSeek-R1-Distill-Qwen-32B 到 int8
#3200 opened Mar 1, 2025 by SolomonLeon
1
LMDeploy Lite vs LLM Compressor
#3199 opened Mar 1, 2025 by radna0
3
[Feature] 看起来ledeploy好像天然支持替换矩阵乘法的计算。deepGEMM 刚刚发布了。怎么用
#3191 opened Feb 26, 2025 by xiezhipeng-git
[Feature] accelerate QwenEncoder
#3185 opened Feb 25, 2025 by abc8350712
多轮对话的batch推理
#3184 opened Feb 25, 2025 by wzczc
1
enable_prefix_caching LMDeploy vs vLLM
#3182 opened Feb 24, 2025 by radna0
@lvhan028
2
[Bug] 将InternVL2_5-26B-AWQ转换成turbomind之后使用turbomind引擎 部署 api请求图片解析，参数传递url与base64均报错-无法进行图片识别
#3169 opened Feb 21, 2025 by Gierry
@lvhan028
[Bug] serve does nothing when launching Mistral Small 3 AWQ
#3167 opened Feb 20, 2025 by anunknowperson
3 tasks done
2
[Bug] non-async call in async fn
#3160 opened Feb 19, 2025 by lz1998
3 tasks done
@grimoire
1
lmdeploy对DeepSeek-R1-Distill-Llama-70B进行api推理时，使用H100的两张显卡，共160G，会出现out of memory
#3154 opened Feb 19, 2025 by winni0
3 tasks done
@lvhan028
2
[Bug] Encountering torch.OutOfMemoryError During int8 Quantization
#3145 opened Feb 16, 2025 by SolomonLeon
3 tasks done
@AllentDan
1
[Bug] api 流式批处理bug 只能得到一个结果，然后卡死。不得不超时强制取消
#3144 opened Feb 15, 2025 by xiezhipeng-git
3 tasks done
@grimoire
11
OOM when use InternVL2_5-1B-MPO
#3143 opened Feb 14, 2025 by BobHo5474
@lvhan028
12
[Feature] old version of outlines 0.0.46, break other packages awaiting response Stale
#3141 opened Feb 13, 2025 by devops724
@AllentDan
6
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.