MiniCPM4 Collection MiniCPM4: Ultra-Efficient LLMs on End Devices • 12 items • Updated 1 day ago • 37
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling Paper • 2502.14856 • Published Feb 20 • 8
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs Paper • 2502.12085 • Published Feb 17 • 4