conftrace_

decoding

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prefill (2) encodings (2) quantization (2) global predictor (1) heatmaps (1) throughput (1) llm-optimized npu (1) nvidia gpus (1) normalized mean squared error (1) colocation (1)

Papers

COExpander: Adaptive Solution Expansion for Combinatorial Optimization ICML 2025 Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders ICML 2025 Progressive Mixed-Precision Decoding for Efficient LLM Inference ICLR 2025 Accelerating Federated Learning with Quick Distributed Mean Estimation ICML 2024 MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving ICML 2024