Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch
Abhishek Ghosh, Ajay Nayak, Ashish Panwar +1
Machine learning (ML) workloads launch hundreds to thousands of short-running GPU kernels per iteration. With GPU compute throughput growing rapidly, CPU-side launch latency of ker…
cs.LG2024
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Ramya Prabhu, Ajay Nayak, Jayashree Mohan +2
PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation -- a phe…