conftrace_

large language model inference

5 papers

Explore in graph

Also known as

LLM INFERENCE

Co-occurring keywords

large language model (13587) batch scheduling (4) throughput latency tradeoff (1) gpu compute utilization (1) inference scheduler (1) multi-fidelity optimization (33) modular framework (21) cost reduction (12) token-level alignment (6) lookup table (13)

Papers

EDSD: Entropy-Driven Design for Faster Speculative Decoding ACL 2026
EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference EMNLP 2025
Pushing the Limits of BFP on Narrow Precision LLM Inference AAAI 2025
Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible LLM Inference EMNLP 2025
Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve OSDI 2024