10 papers
Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
Sudhanshu Agrawal, Risheek Garrepalli, Raghavv Goel +3
Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token-generation rates…
Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
Raghavv Goel, Mukul Gagrani, Mingu Lee +1
Large Language Models (LLMs) possess latent multi-token prediction (MTP) abilities despite being trained only for next-token generation. We introduce ESP (Embedding-Space Probing),…
QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill
Dalton Jones, Junyoung Park, Matthew Morse +3
We present QUOKA: Query-oriented KV selection for efficient attention, a training-free and hardware agnostic sparse attention algorithm for accelerating transformer inference under…
Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs
Wentao Ni, Kangqi Zhang, Zhongming Yu +7
As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse atte…
Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity
Aayush Gautam, Mukul Gagrani, Junyoung Park +3
The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-…
KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
Junyoung Park, Dalton Jones, Matthew J Morse +3
We demonstrate that geometrically distinctive keys during LLM inference tend to have high attention scores. Based on the phenomenon we propose KeyDiff, a training-free KV cache evi…