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.
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.
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 kernels for 91.1% of problems and independently verified speedups on 22 of 56, including three convolutions, with a median of 1.235x. Open-weigh...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
