Conference
When Smaller Models Run Slower: Hardware Efficiency Bottlenecks in VLM Inference on Unified Memory
| Title: | When Smaller Models Run Slower: Hardware Efficiency Bottlenecks in VLM Inference on Unified Memory |
|---|---|
| Authors: | Harsh, Fnu, Jarsania, Jasmin, Nagwani, Aakansha, Behl, Smarth, Singh, Mantek, Gupta, Akash |
| Source: | 2026 IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC) Computing and Communication Workshop and Conference (CCWC), 2026 IEEE 16th Annual. :0462-0469 Jan, 2026 |
| Relation: | 2026 IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC) |
| Database: | IEEE Xplore Digital Library |
| ISBN: | 9798331593971 9798331593988 |
|---|---|
| DOI: | 10.1109/CCWC67433.2026.11393753 |