Technical deep-dives, product updates, and insights from the Cumulus team.
How Cumulus built a production pipeline for consistent AI-generated game previews using best-of-N sampling, deterministic rendering, pairwise judging, supervised fine-tuning, and online reinforcement learning with GRPO.
Cheap GPU inference for AI models: we ran 5 VLMs on one GPU and matched Together AI's throughput at a fraction of the cost. Serverless GPU vs dedicated GPU economics.
How Cumulus built the fastest GPU inference runtime for NVIDIA GH200 — 7,167 tok/s on a single chip. Coherent CUDA graphs, eager KV writeback, and phantom-tile attention scheduling.
How Cumulus built a production pipeline for consistent AI-generated game previews using best-of-N sampling, deterministic rendering, pairwise judging, supervised fine-tuning, and online reinforcement learning with GRPO.
What we found inside Qwen3.5's hybrid Mamba-Transformer weights and what it took to make the gated delta rule fast on GH200 — from matrix-valued recurrences to mixed batch state corruption.
Cheap GPU inference for AI models: we ran 5 VLMs on one GPU and matched Together AI's throughput at a fraction of the cost. Serverless GPU vs dedicated GPU economics.
How Cumulus built the fastest GPU inference runtime for NVIDIA GH200 — 7,167 tok/s on a single chip. Coherent CUDA graphs, eager KV writeback, and phantom-tile attention scheduling.
Cumulus Labs is building the cheapest serverless GPU cloud for AI model hosting. Here's why dedicated GPU instances waste money and how pay-per-second GPU inference changes the economics.