5 papers
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
Tianyu Wu, Yu Yao, Zhenting Qi +7
Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters su…
Coach: Exploiting Temporal Patterns for All-Resource Oversubscription in Cloud Platforms
Benjamin Reidys, Pantea Zardoshti, Íñigo Goiri +16
Cloud platforms remain underutilized despite multiple proposals to improve their utilization (e.g., disaggregation, harvesting, and oversubscription). Our characterization of the r…
ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
Yifan Qiao, Shu Anzai, Shan Yu +10
Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identi…
DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency
Haoran Ma, Yifan Qiao, Shi Liu +7
Despite being a powerful concept, distributed shared memory (DSM) has not been made practical due to the extensive synchronization needed between servers to implement memory cohere…
A Tale of Two Paths: Toward a Hybrid Data Plane for Efficient Far-Memory Applications
Lei Chen, Shi Liu, Chenxi Wang +9
With rapid advances in network hardware, far memory has gained a great deal of traction due to its ability to break the memory capacity wall. Existing far memory systems fall into…