Latest stories
Modal has implemented a syscall-based detection tool named seccheck to identify and prevent crypto-mining abuses, ensuring GPU resources are available for legit...
Learn how to effectively run GPU jobs using Modal in your Airflow workflows, enhancing scalability and simplifying setup.
The Prompt Olympics showcased how expert prompt engineering can enhance code generation and virtual agent control through competitive challenges.
Modal introduces key updates including region selection for functions, a new Datadog integration, and lower latency for improved performance.
This exploration shows how scaling search techniques with the LLaMA model can match or surpass the performance of GPT-4o in coding tasks, highlighting practical...
Modal has cut GPU prices by 15-30% while updating its CPU/memory billing practices, aiming to enhance affordability for AI developers.
Modal's new interactive code playground allows users to execute code easily in the cloud, featuring robust tutorials but constrained by its environment.
Modal's latest updates include app rollbacks, dynamic request batching for efficiency, TCP tunneling in Sandboxes, and reduced pricing for CPU and GPUs.
This article outlines how to create a cost-efficient analytics stack using Modal, dlt, and dbt, highlighting data loading, transformation, and deployment strate...
Dynamic batching can significantly improve the efficiency of machine learning workloads, offering up to 2.8x increased throughput with minimal code changes.
Explore a hybrid search application utilizing MongoDB, Modal, and Clay for satellite image analysis of California, showcasing data integration and real-time cap...
AI's demand for GPU compute is surging, but supply challenges exist. Exploring the shift to on-demand GPU models highlights implications for startups and the in...
Tidbyt, known for its programmable LED screens, joins Modal to leverage mutual strengths in cloud infrastructure and customer acquisition.
Modal introduces new features including static IP proxies, Slack integration for alerts, and a real-time usage dashboard for effective resource management.
OpenArt has efficiently scaled its AI image generation platform using Modal, overcoming limitations of traditional API providers and cloud infrastructure.
Modal's implementation of a Go-based VPN proxy, vprox, enables static IP addresses for serverless containers, ensuring reliable connections and simplified acces...
A leading European soccer team enhanced its data processing efficiency and reduced costs by 50% through improved infrastructure and innovative batch processing.
Modal's internal hackathon showcased innovative projects, including AI tools and latency reduction strategies, enhancing productivity and real-time applications...
Explore how fine-tuning large language models enhances task performance, reduces costs, and discover leading frameworks for implementation.
Modal users can now access NVIDIA L40S GPUs, offering enhanced memory and speed advantages over the A10 GPU for demanding inference tasks.