Modal
25 stories
ModalToolsLaunching a trillion-parameter model at Sakana AI Deploying a ~1-trillion parameter Mixture-of-Experts (MoE) model for API inference is a classic systems challenge. At full FP16 or BF16 precision, the memory footprint requires very large clusters.
ModalToolsIntroducing our Training API Spindle is an open-source API for training and fine-tuning open models — deploy a server with a single command and run any Tinker-compatible training code against it.
ModalToolsGet started with LLM training on Modal Reinforcement learning for LLMs is hard, so we built Modal Dojo — a library that gives you the building blocks, tuned defaults, and observability to get started with production-grade LLM training.
ModalToolsServerless routing made sticky Voice agents, multiplayer games, and other workloads can now build on Sticky Sessions. Achieve strong affinity without losing autoscaling. Here’s how we built this on Modal Servers.
ModalToolsNVIDIA Vera CPUs double throughput for Modal Sandboxes We benchmarked NVIDIA's new Arm-based Vera CPU on agentic Sandbox workloads. Under heavy load, it completes far more tasks than the x86 and Graviton alternatives, without sacrificing latency.
ModalToolsHow Legora runs 2,000 parallel agent evals on Modal Sandboxes To test a legal agent that works for hours across thousands of documents, Legora boots its entire application, pinned to a specific commit, inside a separate Modal Sandbox for every eval run.
ModalToolsBuilding fast filesystems for VMs How we made VM Sandbox filesystems fast by speaking in blocks instead of files.
ModalToolsAugment Your LiveKit Agent with Modal GPUs How to run a LiveKit video avatar with open-weights models on Modal GPUs, using Sticky Sessions for container affinity.
ModalToolsMuse Spark Open is now available on Modal Muse Spark Open, a coding-optimized multimodal model from Meta, is now available on Modal Auto Endpoints.
ModalToolsModal crosses $1B in Annualized Run Rate and raises $750M Series D Modal has crossed $1B in annualized run rate and raised a $750M Series D led by Accel to build new infrastructure for AI applications. We can't think of a better time to be building software.
ModalToolsToward RL on mixed-precision, mixed-accelerator samplers We trained a model on agentic coding tasks using fully asynchronous RL and mixed-precision, mixed-accelerator samplers.
ModalToolsEndpoint Candidates: evaluate and promote inference endpoints Test and promote inference endpoints to evaluate quality, latency, throughput, and cost.
ModalToolsTypeSafe AI scales Jev to trillions of tokens in three days on Modal TypeSafe AI launched Jev, a new class of AI model built for automation, and scaled to trillions of tokens over a weekend on Modal.
ModalToolsModal Clusters are generally available Multi-node GPU clusters with RDMA, gang scheduled from Modal's shared capacity pool and billed by the second, behind a single decorator.
ModalToolsVM Sandboxes: Full computers for agents VM Sandboxes are built for those who need to give their agents the power of a full computer.
ModalToolsRuntime Roundup: VM Sandboxes, Multi-node clusters, and more Everything announced live at Modal's inaugural conference, Runtime.
ModalToolsSidecars: A low-latency trust boundary for Sandboxes Sidecars are isolated containers that run alongside your main Sandbox on the same host.
ModalToolsQuail: Speeding up AI-SQL by jointly optimizing query planner and inference engine Maximizing perf on AI-SQL queries with the KV-optimal left-deep join
ModalToolsHow to serve trillions of tokens for trillion-parameter coding agents Learn how we optimized performance and efficiency serving the workload that is changing software engineering forever — and you can too.
ModalToolsProduct updates: Sandbox Sidecars, new models, a refreshed dashboard, and more Recent product updates from Modal and news from around the community.
ModalToolsOne compute platform for end-to-end training at Markov Robotics Markov Robotics is teaching robots to tackle complex tasks with fewer than ten hours of robot data, using Modal to power video processing, world model training, and real-time inference—and run ten…
ModalToolsModal is expanding in Europe with our new London office Modal is expanding, and hiring on all fronts across Europe.
ModalToolsHow Botika runs full-stack generative AI on Modal Botika is building the next generation of tooling for agentic e-commerce brands, backed by a fleet of custom models trained and served on Modal.
ModalToolsQwen3.8-2.4T-A95B now available on Modal Qwen3.8-2.4T-A95B by Alibaba, with a 1M token context window, is now available via Modal Auto Endpoints.
Nothing matches this filter yet.