Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face
Explorar
Noticias de IA
676 elementos — filtrados, clasificados y sin duplicados
Parquet Content-Defined Chunking
Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨
Fast LoRA inference for Flux with Diffusers and PEFT
Accelerate a World of LLMs on Hugging Face with NVIDIA NIM
Five Big Improvements to Gradio MCP Servers
ScreenEnv: Deploy your full stack Desktop Agent
Building the Hugging Face MCP Server
Creating custom kernels for the AMD MI300
Upskill your LLMs With Gradio MCP Servers
Efficient MultiModal Data Pipeline
Three Mighty Alerts Supporting Hugging Face’s Production Infrastructure
Transformers backend integration in SGLang
Groq on Hugging Face Inference Providers 🔥
How Long Prompts Block Other Requests - Optimizing LLM Performance
Featherless AI on Hugging Face Inference Providers 🔥
Learn the Hugging Face Kernel Hub in 5 Minutes
Introducing Training Cluster as a Service - a new collaboration with NVIDIA
ScreenSuite - The most comprehensive evaluation suite for GUI Agents!
Real-Time AI Sound Generation on Arm: A Personal Tool for Creative Freedom
No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL
Tiny Agents in Python: a MCP-powered agent in ~70 lines of code
nanoVLM: The simplest repository to train your VLM in pure PyTorch
Exploring Quantization Backends in Diffusers
The Transformers Library: standardizing model definitions
Improving Hugging Face Model Access for Kaggle Users
Blazingly fast whisper transcriptions with Inference Endpoints
How to Build an MCP Server with Gradio
PipelineRL
Tiny Agents: an MCP-powered agent in 50 lines of code