Skip to content
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

关于InternVL TurbomindEngine 的疑惑 #3111

Open
chenzhengda opened this issue Feb 6, 2025 · 1 comment
Open

关于InternVL TurbomindEngine 的疑惑 #3111

chenzhengda opened this issue Feb 6, 2025 · 1 comment
Assignees

Comments

@chenzhengda
Copy link

chenzhengda commented Feb 6, 2025

据我了解 TurbomindEngine 推理InternVL时VIT和VLM部分应该是共享(抢占)GPU资源的,想请教一下这是否会影响TTFT?实际benchmark下来也有部分请求的TTFT会很长,这是正常的表现吗?

@lvhan028
Copy link
Collaborator

lvhan028 commented Feb 6, 2025

从目前 profile 的情况来看,对于 VLM 模型的推理,LMDeploy对请求的调度处理的不好,会导致 TTFT 变挺长的。我们觉得和 VIT 部分的关系没有多大。

@lvhan028 lvhan028 self-assigned this Feb 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants