Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand
•
30
Community Blog & Articles
Community Articles
view all
NVIDIA Releases Improved Pretraining Dataset: Preserves High Value Math & Code, and Augments with Multi-Lingual
3
August 18, 2025
kernelskernels-communityguide
From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels
88
August 18, 2025
mcpresearchguide
MCP for Research: How to Connect AI to Research Tools
64
August 18, 2025
Kimina-Prover-RL
12
August 14, 2025
Arm & ExecuTorch 0.7: Bringing Generative AI to the masses
2
August 13, 2025
Neural Super Sampling is here!
4
August 12, 2025
researchllmevaluation
TextQuests: How Good are LLMs at Text-Based Video Games?
36
August 12, 2025
open-sourceLLMcommunity
🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?
- +5
20
August 12, 2025
NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks
75
August 11, 2025
datasetsopen-sourcecommunity
Introducing AI Sheets: a tool to work with datasets using open AI models!
- +2
106
August 8, 2025
transformersllmguide
Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training
- +1
85
August 8, 2025
trlvlmvision
Vision Language Model Alignment in TRL ⚡️
- +1
101
August 7, 2025
openaigptgpt-oss
Welcome GPT OSS, the new open-source model family from OpenAI!
- +8
509
August 5, 2025
Measuring Open-Source Llama Nemotron Models on DeepResearch Bench
5
August 4, 2025
NEW
Articles from
Team
or
organizations will get promoted to the main section.
Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand
•
30
Norm-Preserving Biprojected Abliteration
•
47
TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
•
14
Code a simple RAG from scratch
•
260
**An Edge-First Generalized LLM LoRA Fine-Tuning Framework for Heterogeneous GPUs**
•
11
Curating datasets directly on the Hub
•
22
Building Jobly: Semantic Job Matching with RAG and Vector Embeddings
•
10
Gemini-3 Benchmarkathon
•
9
Uncensor any LLM with abliteration
•
733
How MCP Blockly Makes MCP Server Creation Accessible for Everyone
•
7
Ellora: Enhancing LLMs with LoRA - Standardized Recipes for Capability Enhancement
•
6
Building and evaluating Multimodal Rerankers
•
6
Mastering Tensor Dimensions in Transformers
•
120
From GRPO to DAPO and GSPO: What, Why, and How
•
64
DeepFabric: Generate, Train and Evaluate with Datasets curated for Model Behavior Training.
•
5
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
188
**Bringing Math to Life: Building StepWise Math for the MCP Hackathon**
•
4
SARLO-80: Worldwide Slant SAR Language Optic Dataset at 80 cm Resolution
•
4
makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch
•
109
GSMA Open-Telco LLM Benchmarks 2.0: The first dedicated LLM Evaluation for Telecoms
•
22