view article Article Continuous batching from first principles +1 ror, ArthurZ, mcpotato • Nov 25, 2025 • 455
view article Article Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥 +5 julien-c, kramp, reach-vb, sbrandeis, albertworks, viktor-hu, cchevli • Feb 18, 2025 • 102
PocketDoc/Dans-PersonalityEngine-V1.2.0-24b Text Generation • 24B • Updated May 23, 2025 • 110 • • 184
view article Article Welcome to Inference Providers on the Hub 🔥 +5 burkaygur, zeke, aton2006, hassanelmghari, sbrandeis, kramp, julien-c • Jan 28, 2025 • 499
view post Post 2,085 Only a single RTX 4090 running model pre-training is really slow, even for small language models!!! (https://huggingface.co/collections/JingzeShi/doge-slm-677fd879f8c4fd0f43e05458) See translation 2 replies · 👀 8 8 🤯 6 6 👍 4 4 + Reply