11 papers · 1 filter
Characterizing High Bandwidth Flash for LLM Serving
Zack Yu, Chloe Wong, Coleman Hooper +7
Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, memory capacity and bandwidth…
AsyncOPD: How Stale Can On-Policy Distillation Be?
Wonjun Kang, Kevin Galim, Seunghyuk Oh +9
On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Li…
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Minseo Kim, Minjae Lee, Seunghyuk Oh +7
Reinforcement learning (RL) has become a representative post-training paradigm for large language models (LLMs), enabling strong reasoning and agentic capabilities. However, rollou…
TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs
Minjae Lee, Wonjun Kang, Byeongkeun Ahn +6
Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplo…
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
Yuchen Zeng, Shuibai Zhang, Wonjun Kang +9
Large Reasoning Models (LRMs) are Large Language Models (LLMs) explicitly trained to generate long-form Chain-of-Thoughts (CoTs), achieving impressive success on challenging tasks…
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
Wonjun Kang, Kevin Galim, Seunghyuk Oh +8
While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inferen…
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Aditya Tomar, Coleman Hooper, Minjae Lee +7
Although LLM inference has emerged as a critical workload for many downstream applications, efficiently inferring LLMs is challenging due to the substantial memory footprint and ba…
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
Wonjun Kang, Kevin Galim, Yuchen Zeng +3
State Space Models (SSMs) have emerged as efficient alternatives to Transformers, mitigating their quadratic computational cost. However, the application of Parameter-Efficient Fin…
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
Thomas Zeng, Shuibai Zhang, Shutong Wu +13
Process Reward Models (PRMs) have proven effective at enhancing mathematical reasoning for Large Language Models (LLMs) by leveraging increased inference-time computation. However,…
Parameter-Efficient Fine-Tuning of State Space Models
Kevin Galim, Wonjun Kang, Yuchen Zeng +2
Deep State Space Models (SSMs), such as Mamba (Gu & Dao, 2024), have become powerful tools for language modeling, offering high performance and linear scalability with sequence len…
Can MLLMs Perform Text-to-Image In-Context Learning?
Yuchen Zeng, Wonjun Kang, Yicong Chen +2
The evolution from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs) has spurred research into extending In-Context Learning (ICL) to its multimodal counterp…