PhD in computer science with a focus on high performance computing. Now working at Google on inference performance on TPUs.
-
Google
- Seattle, WA
- patemotter.com
Pinned Loading
-
AI-Hypercomputer/maxtext
AI-Hypercomputer/maxtext PublicA simple, performant and scalable Jax LLM!
-
mlcommons/inference
mlcommons/inference PublicReference implementations of MLPerf™ inference benchmarks
-
AI-Hypercomputer/JetStream
AI-Hypercomputer/JetStream PublicJetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
-
GoogleCloudPlatform/ml-auto-solutions
GoogleCloudPlatform/ml-auto-solutions PublicA simplified and automated orchestration workflow to perform ML end-to-end (E2E) model tests and benchmarking on Cloud VMs across different frameworks.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.