对微调的Qwen2-7B模型做量化，为什么使用量化后的模型推理时间变慢，显存占用无明显提升？ #650

Sign in to view logs

Summary
Jobs
- label_issue
Run details
- Usage
- Workflow file

Triggered via issue July 22, 2024 07:05

opened #4920 26082fc

Status Success

Total duration 11s

Artifacts –

label_issue.yml

on: issues