lmdeploy icon indicating copy to clipboard operation
lmdeploy copied to clipboard
Published 1 month ago • verified publisher icon InternLM

[Feature] When will TurboMind backend support InternVL3.5-Flash series models?

Open jianhuiliao opened this issue 2 months ago • 0 comments

Motivation

Currently LMDeploy only supports InternVL3.5-Flash series models with PyTorch backend, which did not bring the expected performance improvement compared with InternVL3.5 series models with TurboMind backend. When will TurboMind backend support InternVL3.5-Flash series models?

Related resources

No response

Additional context

No response

jianhuiliao avatar Oct 27 '25 09:10 jianhuiliao