Tinker changed how people do post-training. We're big fans, and so are many of the teams we work with. But as those teams scale up, they keep raising the same two problems: per-token pricing gets expensive quickly, and you’re limited to the models and features the provider decides to support. We think a good API deserves more than one implementation. Today we're releasing Spindle, an open-source, Tinker-compatible training server that runs in your Modal workspace. Your existing Tinker scripts run unchanged, and because you own the server, you pay for GPU time instead of tokens.

Performant reinforcement learning is a hard infrastructure and research problem. We’ve recently made on-demand multi-node clusters available and showed how to take advantageous of heterogeneous sampling compute. But there still exists the need for high-fidelity environments, clear and robust reward functions, and tuned training recipes that actually work. Most teams are actually nearly there! With an agent harness deployed in production and evals/agent traces collected from that deployment, you just need an easy way to start training your data. So we built a training library that gives you the building blocks, tuned defaults, and observability you need for easy, production-grade LLM training. It’s available now. All it takes is a prompt.

We got our hands on @nvidia's new Vera CPU and put it to the test. We built a benchmark using real-world agentic workloads to see how it performs under contention. In early tests, Vera delivered up to 2x the throughput of comparable x86 hardware, maintaining low latency even as hundreds of concurrent workloads competed for resources. For Modal Sandboxes, that could mean running more agents in parallel without sacrificing latency.