AI
From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub
Hugging Face Blog · 2025-02-12
Related items
AIHugging Face Blog
Rearchitecting Hugging Face Uploads and Downloads
AIHugging Face Blog
From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
AIHugging Face Blog
Migrating the Hub from Git LFS to Xet
AIHugging Face Blog
Hugging Face and AMD partner on accelerating state-of-the-art models for CPU and GPU platforms
AIarXiv cs.LG
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow mixing. In this...
AIHugging Face Blog