workers-ai | byteiota

Tag: workers-ai

Cloudflare Unweight lossless BF16 LLM weight compression visualization on H100 GPU

Cloud & DevOps

Cloudflare Unweight: Lossless LLM Compression on H100

Cloudflare's Unweight compresses LLM BF16 weights 15–22% with zero quality loss. Open-source H100 GPU kernels, ...

2 hours ago

Cloudflare edge network globe with vision AI neural network nodes representing Moondream 3.1 sub-second vision inference

AI & Development

Moondream 3.1 on Cloudflare Workers AI: Vision Inference Under 500ms

Cloudflare added Moondream 3.1 to Workers AI — a 9B MoE vision model that runs ...

July 15, 2026