Conference
GPU-Parallel Binary Tree Token Merging for Efficient Large Language Model Inference
| Τίτλος: | GPU-Parallel Binary Tree Token Merging for Efficient Large Language Model Inference |
|---|---|
| Συγγραφείς: | Sanli, Ibrahim Taha, Akdag, Ali |
| Πηγή: | 2026 2nd International Symposium on AI-Driven Engineering Systems (ISADES) AI-Driven Engineering Systems (ISADES), 2026 2nd International Symposium on. :1-5 Jun, 2026 |
| Relation: | 2026 2nd International Symposium on AI-Driven Engineering Systems (ISADES) |
| Βάση Δεδομένων: | IEEE Xplore Digital Library |
καταχωρήστε σχόλιο πρώτοι!