2 papers
cs.AI2026
Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits
Gaurav Agarwal, Ashish Garg, Isha Singhal
Concurrent autoregressive inference creates a fundamental interference problem: prefilling a newly arrived long prompt can delay tokens for requests that are already decoding. Fixe…
cs.DC2026
How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach?
Gaurav Agarwal, Ashish Garg, Isha Singhal
Language models can now write GPU kernels that outperform PyTorch. We evaluate five model configurations on KernelBench level 1 and find that a frontier model produces correct kern…