Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand
•
58
Community Blog & Articles
Community Articles
view all
Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance
52
December 9, 2025
swifthubopen-source
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
25
December 5, 2025
llmreasoningagents
DeepMath: A lightweight math reasoning Agent with smolagents
22
December 4, 2025
llmfine-tuningopen-source
We Got Claude to Fine-Tune an Open Source LLM
414
December 4, 2025
Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications
18
December 2, 2025
transformersv5community
Transformers v5: Simple model definitions powering the AI ecosystem
233
December 1, 2025
diffusersfluxquantization
Diffusers welcomes FLUX-2
- +4
160
November 25, 2025
transformerspytorchoptimization
Continuous batching from first principles
261
November 25, 2025
Building Deep Research: How we Achieved State of the Art
21
November 24, 2025
OVHcloud on Hugging Face Inference Providers 🔥
69
November 24, 2025
llmexperimentationfine-tuning
20x Faster TRL Fine-tuning with RapidFire AI
24
November 21, 2025
audiospeechleaderboard
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
22
November 21, 2025
llmcoremlmlx
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms
33
November 20, 2025
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
29
November 19, 2025
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand
•
58
TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
•
17
How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day
•
14
AI Energy Score v2: Refreshed Leaderboard, now with Reasoning 🧠
•
9
Ellora: Enhancing LLMs with LoRA - Standardized Recipes for Capability Enhancement
•
11
Norm-Preserving Biprojected Abliteration
•
52
Code a simple RAG from scratch
•
263
**An Edge-First Generalized LLM LoRA Fine-Tuning Framework for Heterogeneous GPUs**
•
14
Making Model Tuning Accessible: This is what we built observing 100s of users tune models!
•
6
I Built a RAG System That Listens to Live BBC News and Answers Questions About "What Happened 10 Minutes Ago"
•
6
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
192
🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI
•
30
The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
•
51
DeepFabric: Generate, Train and Evaluate with Datasets curated for Model Behavior Training.
•
5
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
•
255
Small Language Models (SLM): A Comprehensive Overview
•
110
From GRPO to DAPO and GSPO: What, Why, and How
•
67
Build Hallucination-Free RAG with Verbatim
•
7
Engineering Notes: Training a LoRA for Z-Image Turbo with the Ostris AI Toolkit
•
5
Muon vs MuonClip vs Muon+AdamW for Fine-Tuning
•
4