6 papers
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
Jonathan Li, Nasim Farahini, Evgenii Iuliugin +19
The proliferation of 100B+ parameter Large Language Models (LLMs) with 100k+ context length support have resulted in increasing demands for on-chip memory to support large KV cache…
Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
Shubhangi Upasani, Chen Wu, Jay Rainton +4
Test-time adaptation enables large language models (LLMs) to modify their behavior at inference without updating model parameters. A common approach is many-shot prompting, where l…
Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
Shubhangi Upasani, Ravi Shanker Raju, Bo Li +5
Prompt length is a major bottleneck in agentic large language model (LLM) workloads, where repeated inference steps and multi-call loops incur substantial prefill cost. Recent work…
Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
Fenglu Hong, Ravi Raju, Jonathan Lingjie Li +5
Speculative decoding is an effective method for accelerating inference of large language models (LLMs) by employing a small draft model to predict the output of a target model. How…
LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
Guangtao Wang, Shubhangi Upasani, Chen Wu +5
Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and…
Composition of Experts: A Modular Compound AI System Leveraging Large Language Models
Swayambhoo Jain, Ravi Raju, Bo Li +8
Large Language Models (LLMs) have achieved remarkable advancements, but their monolithic nature presents challenges in terms of scalability, cost, and customization. This paper int…