nmt bash efficiency speech serving
2026
- CRE-Router: Cost-Aware LLM Serving » 28 Oct 2026
- Disaggregated Serving » 23 Oct 2026
2025
- Iterative Layer Pruning for Efficient Inference » 17 Nov 2025
2024
2022
- Purely Synthetic Bilingual Data for Machine Translation? » 12 Dec 2022