Patel, T. P. (2026). Memory-Efficient Speculative Decoding for Large Language Model Inference on Commodity GPUs. 2026 IEEE 15th International Conference on Communication Systems and Network Technologies (CSNT), Communication Systems and Network Technologies (CSNT), 2026 IEEE 15th International Conference on, 390. https://doi.org/10.1109/CSNT69054.2026.11502509
Παραπομπή σε μορφή Chicago (17η εκδ.)Patel, Tejas Pravinbhai. "Memory-Efficient Speculative Decoding for Large Language Model Inference on Commodity GPUs." 2026 IEEE 15th International Conference on Communication Systems and Network Technologies (CSNT), Communication Systems and Network Technologies (CSNT), 2026 IEEE 15th International Conference on 2026: 390. https://doi.org/10.1109/CSNT69054.2026.11502509.
Παραπομπή σε μορφή MLA (9th εκδ.)Patel, Tejas Pravinbhai. "Memory-Efficient Speculative Decoding for Large Language Model Inference on Commodity GPUs." 2026 IEEE 15th International Conference on Communication Systems and Network Technologies (CSNT), Communication Systems and Network Technologies (CSNT), 2026 IEEE 15th International Conference on, 2026, p. 390, https://doi.org/10.1109/CSNT69054.2026.11502509.