We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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?
The text was updated successfully, but these errors were encountered:
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。
Sorry, something went wrong.
lvhan028
No branches or pull requests
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?
The text was updated successfully, but these errors were encountered: