Search Results for author:
Found 5 papers, 2 papers with code
Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding
We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs).
LoopTune: Optimizing Tensor Computations with Reinforcement Learning
Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries introduce unsustainable costs.
LoopStack: a Lightweight Tensor Algebra Compiler Stack
We present LoopStack, a domain specific compiler stack for tensor operations, composed of a frontend, LoopTool, and an efficient optimizing code generator, LoopNest.
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
What is needed is an easy, reusable experimental infrastructure for real world compiler optimization tasks that can serve as a common benchmark for comparing techniques, and as a platform to accelerate progress in the field.
Semisupervised Learning on Heterogeneous Graphs and its Applications to Facebook News Feed
We show that the HELP algorithm improves the predictive performance across multiple tasks, together with semantically meaningful embedding that are discriminative for downstream classification or regression tasks.
