Author

Ashish Garg

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits

Decode-Latency Feedback Prefill is introduced, a model-free controller that changes only prefill work that overlaps active decodes that defines the boundary of the contribution and motivates a completion-timed controller for concurrent CPU and on-device inference.

Gaurav Agarwal, Ashish Garg, Isha Singhal · 0 citations

#artificial intelligence Preprint Sep 2026

How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach?

Language models can now write GPU kernels that outperform PyTorch, and a question the literature does not: what fraction of a real model's wall clock do such kernels govern?

Gaurav Agarwal, Ashish Garg, Isha Singhal · 0 citations