9 papers
Thought-Level Beam Search for Reasoning
Lijie Yang, Hongyin Luo, Jiawei Zhao +2
Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question fr…
SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification
Pragaash Ponnusamy, Shivam Sahni, Jue Wang +1
Sampling in LLM inference comprises a combinatorial set of logit processing, token selection, and verification operations for speculative decoding. However, existing implementation…
Search Your Block Floating Point Scales!
Tanmaey Gupta, Hayden Prairie, Xiaoxia Wu +10
Quantization has emerged as a standard technique for accelerating inference for generative models by enabling faster low-precision computations and reduced memory transfers. Recent…
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
Jinda Jia, Jisen Li, Zhongzhu Zhou +8
KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent wor…
Introspective Diffusion Language Models
Yifan Yu, Yuqing Jian, Junxiong Wang +12
Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR mo…
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou +16
We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, whi…
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Junxiong Wang, Fengxiang Bie, Jisen Li +14
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone…
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
Zelei Shao, Vikranth Srivatsa, Sanjana Srivastava +12
Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where…
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
Costin-Andrei Oncescu, Qingyang Wu, Wai Tong Chung +5
An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subse…