Qwen2.5VL 量化后，能否在V100上运行？ #1

Open

opened

on Jul 15, 2025

Qwen2.5VL 是可以直接在V100运行的，量化后，部署时发现几种scheme都超过了V100的计算能力。比较好奇是哪里引入的计算导致V100的算力无法推理

to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests