Mixture-of-Kittens: An MoE training megakernel for NVL72

OsamaJaber1 pts0 comments

Cursor on X: "We're open-sourcing Mixture-of-Kittens (MoK), our MoE training megakernel for NVL72s.

It fuses all Mixture-of-Experts communication and computation into a single, fully deterministic kernel, and runs up to 2.37x faster than the strongest public baselines. https://t.co/yHu5E6RXp9" / X<br>Post

Log inSign up

Post

Cursor

@cursor_ai

We're open-sourcing Mixture-of-Kittens (MoK), our MoE training megakernel for NVL72s.

It fuses all Mixture-of-Experts communication and computation into a single, fully deterministic kernel, and runs up to 2.37x faster than the strongest public baselines.

span:not(:empty)~span:not(:empty)]:before:content-['·'] [&>span:not(:empty)~span:not(:empty)]:before:px-1 [&>span:not(:empty)~span:not(:empty)]:before:shrink-0">4:00 PM · Aug 4, 2026159.9KViews

126<br>211<br>2.8K<br>701

span:not(:empty)~span:not(:empty)]:before:content-['·'] [&>span:not(:empty)~span:not(:empty)]:before:px-1 [&>span:not(:empty)~span:not(:empty)]:before:shrink-0 min-w-0 overflow-hidden">Cursor

@cursor_ai

3h

MoK now powers training across tens of thousands of GPUs at Cursor.

In production, it raised end-to-end training throughput by 1.41x over our previous DeepEP-based stack.

226<br>svg]:size-5 text-body hover:bg-mix-current hover:bg-mix-amount-10 active:bg-mix-current active:bg-mix-amount-15 focus-visible:bg-mix-current focus-visible:bg-mix-amount-10 outline-current -m-2 shrink-0 cursor-pointer border-transparent p-0 text-body size-9 [&>svg]:size-[1.25em] [&>[data-engagement-icon]]:size-[1.25em] group-hover:bg-mix-current group-hover:bg-mix-amount-10" aria-label="View count" type="button" data-state="closed" href="/cursor_ai/status/2084670808337564034/quotes">16K

span:not(:empty)~span:not(:empty)]:before:content-['·'] [&>span:not(:empty)~span:not(:empty)]:before:px-1 [&>span:not(:empty)~span:not(:empty)]:before:shrink-0 min-w-0 overflow-hidden">Cursor

@cursor_ai

3h

Our hope is that this lowers the barrier to AI research, so more labs can train models efficiently.

Here's how we built it:

Mixture-of-Kittens: our open-source MoE megakernel for NVL72s · Cursor

From cursor.com

213<br>svg]:size-5 text-body hover:bg-mix-current hover:bg-mix-amount-10 active:bg-mix-current active:bg-mix-amount-15 focus-visible:bg-mix-current focus-visible:bg-mix-amount-10 outline-current -m-2 shrink-0 cursor-pointer border-transparent p-0 text-body size-9 [&>svg]:size-[1.25em] [&>[data-engagement-icon]]:size-[1.25em] group-hover:bg-mix-current group-hover:bg-mix-amount-10" aria-label="View count" type="button" data-state="closed" href="/cursor_ai/status/2084671209229164810/quotes">15K

span:not(:empty)~span:not(:empty)]:before:content-['·'] [&>span:not(:empty)~span:not(:empty)]:before:px-1 [&>span:not(:empty)~span:not(:empty)]:before:shrink-0 min-w-0 overflow-hidden">Lee Robinson

@leerob

3h

The real mixture of kittens

215<br>svg]:size-5 text-body hover:bg-mix-current hover:bg-mix-amount-10 active:bg-mix-current active:bg-mix-amount-15 focus-visible:bg-mix-current focus-visible:bg-mix-amount-10 outline-current -m-2 shrink-0 cursor-pointer border-transparent p-0 text-body size-9 [&>svg]:size-[1.25em] [&>[data-engagement-icon]]:size-[1.25em] group-hover:bg-mix-current group-hover:bg-mix-amount-10" aria-label="View count" type="button" data-state="closed" href="/leerob/status/2084673771839902061/quotes">7.3K

Log in or sign up for X<br>See what’s happening and join the conversation<br>Continue with phoneContinue with AppleContinue with Google<br>or<br>Log in with username or email

Relevant people

Cursor@cursor_aiFollow<br>Coding agent for building ambitious software

Trending now

span empty current before size hover

Related Articles