3 papers
cs.PF2026
PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving
Omkar Shewale, Deepak Kumar, Divakar Kumar Yadav
Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipelines, agent frameworks, and mu…
cs.LG2026
Hybrid JIT-CUDA Graph Optimization for Low-Latency Large Language Model Inference
Divakar Kumar Yadav, Tian Zhao
Large Language Models (LLMs) have achieved strong performance across natural language and multimodal tasks, yet their practical deployment remains constrained by inference latency…
cs.LG2026
Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs
Divakar Kumar Yadav, Tian Zhao, Deepak Kumar
NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor…