Tag
A page from Modal's LLM Engineer's Almanac that provides an interactive explorer for understanding low-precision floating-point formats like bf16 and fp4.
Modal's infrastructure now enables cost-effective execution of sparse workloads, unlocking long-tail AI use cases previously prohibitive due to underutilized compute costs.
Modal engineers detail their approach to achieving truly serverless GPUs for AI inference, combining cloud buffers, a custom content-addressed filesystem, and CPU/GPU checkpoint/restore to scale replicas in tens of seconds instead of minutes.
Modal announces a partnership with OpenAI Devs and Antler Global to host an Autoresearch Systems Hackathon on May 30th targeting data and compute-intensive challenges.
Modal Jazz is a complete open AI stack using Modal, DeepSeek V4 Pro, and SGLang for self-hosted language model inference, with frontends like OpenCode, OpenClaw, and Vercel AI SDK.