speedups

Otil: Accelerating Diffusion Model Inference via Communication-Efficient Multi-GPU Parallelism CVPR 2026 Accelerating Large Language Model Reasoning via Speculative Search ICML 2025 Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies ICML 2025 Arrow: Accelerator for Time Series Causal Discovery with Time Weaving ICML 2025 Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective ICML 2025 FlatQuant: Flatness Matters for LLM Quantization ICML 2025 GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models ICML 2025 Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding ICML 2025 RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding ICML 2025 TabFlex: Scaling Tabular Learning to Millions with Linear Attention ICML 2025 TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation ICML 2025 Approximate Nearest Neighbor Search with Window Filters ICML 2024 Collage: Light-Weight Low-Precision Strategy for LLM Training ICML 2024 DistiLLM: Towards Streamlined Distillation for Large Language Models ICML 2024 Fast Benchmarking of Asynchronous Multi-Fidelity Optimization on Zero-Cost Benchmarks AutoML 2024 Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization ICML 2024 StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis ICML 2024