Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912226800041984 |
|---|---|
| author | Agarwal, Shubham Iqbal, Saud Mitra, Subrata |
| author_facet | Agarwal, Shubham Iqbal, Saud Mitra, Subrata |
| contents | Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is less effective for generative text-to-image models due to their sensitivity to input prompts and performance degradation caused by large model loading overheads. This work introduces a novel text-to-image inference system that optimally matches prompts across multiple instances of the same model operating at various approximation levels to deliver high-quality images under high loads and fixed budgets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06798 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System Agarwal, Shubham Iqbal, Saud Mitra, Subrata Machine Learning Distributed, Parallel, and Cluster Computing Graphics Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is less effective for generative text-to-image models due to their sensitivity to input prompts and performance degradation caused by large model loading overheads. This work introduces a novel text-to-image inference system that optimally matches prompts across multiple instances of the same model operating at various approximation levels to deliver high-quality images under high loads and fixed budgets. |
| title | Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Graphics |
| url | https://arxiv.org/abs/2502.06798 |