2 papers
cs.PL2026
Agentic Code Optimization via Compiler-LLM Cooperation
Benjamin Mikek, Danylo Vashchilenko, Bryan Lu +1
Generating performant executables from high level languages is critical to software performance across a wide range of domains. Modern compilers perform this task by passing code t…
cs.CV2024
VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
Dezhan Tu, Danylo Vashchilenko, Yuzhe Lu +1
Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-…