Source details
- Original source
- MarkTechPost
- Published
- 2026-08-04
- Primary topic
- Foundation Models
Why it matters
Model launches, benchmark jumps, API upgrades, context window changes, and frontier LLM competition. Use the original source for the full report, then use the directory shortcuts below to compare the products and workflows the story points toward.
What happened
Cursor Research has open-sourced Mixture-of-Kittens (MoK), the MoE training megakernel behind its Composer models. MoK fuses all mixture-of-experts communication and computation into a single deterministic kernel, and runs up to 2.37x faster than the strongest public baseline on GB300 NVL72 racks. It requires Blackwell SM100 or SM103 GPUs, which puts it out of reach for anyone without NVL72 capacity. The post Cursor Open-Sources Mixture-of-Kittens (MoK): A Deterministic MoE Training Megakernel for GB300 NVL72 Racks appeared first on MarkTechPost .
What to do next
Compare the hosted model pages first, then check the related tools and buyer guides before changing workflow standards.
Cursor Research has open-sourced Mixture-of-Kittens (MoK), the MoE training megakernel behind its Composer models. MoK fuses all mixture-of-experts communication and computation into a single deterministic kernel, and runs up to 2.37x faster than the strongest public baseline on GB300 NVL72 racks. It requires Blackwell SM100 or SM103 GPUs, which puts it out of reach for anyone without NVL72 capacity. The post Cursor Open-Sources Mixture-of-Kittens (MoK): A Deterministic MoE Training Megakernel for GB300 NVL72 Racks appeared first on MarkTechPost .
This AimostAll brief summarizes the linked source so readers can scan AI developments quickly and jump to the original reporting when needed.
