Archive - MLOps Newsletter

Tokasaurus and LLM Inference Library Comparisons

Jul 5 •

June 2025

One MegaKernel to rule Llama-1B

Stanford's Hazy Research group recently explored how to maximize the speed of open-source models on modern GPUs, particularly in the challenging…

Jun 21 •

Attention Wasn't All We Needed, we need more

Cosine Autoencoder for Image Restoration

Jun 8 •

May 2025

April 2025

March 2025

Olmo 2 32B is released!

PyTorch Landscape, torch titan, camel and torchcodec are reviewed

Mar 30 •

Modules in Pinterest's HomeFeed

Nemotron-H: A Family of Accurate, Efficient Hybrid Mamba-Transformer Models

Mar 23 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts