Lyu Han comments

Results 512 comments of


                                            Lyu Han

[Bug] ImportError: DLL load failed while importing _turbomind: 找不到指定的模块。

要不你试试源码编译？我们没有euleros的环境

双卡V100 使用 lmdeploy cli 部署InternLM2-Chat-20B服务, 运行一段时间后,请求报错: an illegal memory access was encountered /lmdeploy/src/turbomind/utils/allocator.h:231

"finish_reason": "length" 表示模型一直在生成，停不下来模型是官方的模型么？复现的方式能不能提供下呢？比如 prompt数据，脚本之类的

双卡V100 使用 lmdeploy cli 部署InternLM2-Chat-20B服务, 运行一段时间后,请求报错: an illegal memory access was encountered /lmdeploy/src/turbomind/utils/allocator.h:231

能不能麻烦你升级到 v0.3.0 再试试？我们修了一些bug，可能会解决你遇到的问题。如果还是老样子，我再找下 v100 服务器，尝试复现看看

[Feature] lmdeploy0.1.0，启动后显存占用较大，是什么原因？

预先为kv cache分配的缓存

[Feature] lmdeploy0.1.0，启动后显存占用较大，是什么原因？

https://lmdeploy.readthedocs.io/en/latest/inference/pipeline.html#usage

[Feature] lmdeploy0.1.0，启动后显存占用较大，是什么原因？

使用的是 lmdeploy 的哪个接口呢？

[Bug] sometimes Internal Server Error

This issue is resolved in the latest version v0.4.1. May upgrade lmdeploy to v0.4.1 and try it again

[Bug] Issues Running Vision Language Models in Docker

Hi, @shur-complement Thanks for pointing this issue out. Since vision models might bring in unnecessary dependencies for LLM models, we let users handle them case by case. We have to...

[Bug] Issues Running Vision Language Models in Docker

Can `--no-deps` eliminate conflicts?

[Bug] Issues Running Vision Language Models in Docker

That's very kind of you. Look forward to your PR