epfml

EPFL Machine Learning and Optimization Laboratory Joined Jul 2016 View on GitHub

Stars: 8,192; across 60 public repos
Rank: #4,609; of 94,827 organizations, top 5%

Repositories with 50+ stars

epfml's repositories with their overall rank
Rank	Repository	Language	Stars
32,411	ML_course EPFL Machine Learning Course, Fall 2026	Jupyter Notebook	2,099
45,951	OptML_course EPFL Course - Optimization for Machine Learning - CS-439	Jupyter Notebook	1,490
56,335	sent2vec General purpose unsupervised sentence representations	C++	1,202
59,975	attention-cnn Source code for "On the Relationship between Self-Attention and Convolutional Layers"	Python	1,122
144,098	landmark-attention Landmark Attention: Random-Access Infinite Context Length for Transformers	Python	427
286,740	disco DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning models without sharing any private data.	TypeScript	191
330,611	federated-learning-public-code	Python	161
346,524	powersgd Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727	Python	152
346,524	collaborative-attention Code for Multi-Head Attention: Collaborate Instead of Concatenate	Python	152
346,524	dynamic-sparse-flash-attention	Jupyter Notebook	152
419,393	llm-baselines nanoGPT-like codebase for LLM training	Python	120
508,050	schedules-and-scaling Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"	Python	94
555,233	DenseFormer	Python	84
613,485	ChocoSGD Decentralized SGD and Consensus with Communication Compression: https://arxiv.org/abs/1907.09356	Python	74
713,763	llm-optimizer-benchmark Benchmarking Optimizers for LLM Pretraining. NeurIPS 2026, EurIPS 2025	Python	61
742,413	sparsifiedSGD Sparsified SGD with Memory: https://arxiv.org/abs/1809.07599	Jupyter Notebook	58

Among 94,827 organizations

6.3k–10k stars: 1,979 organizations, including epfml

top 50%top 10%top 1%top 0.1%

Stars along the bottom, and organizations in each band on a log scale

Where the stars are

ML_course 2.1k, 26%OptML_course 1.5k, 18%sent2vec 1.2k, 15%attention-cnn 1.1k, 14%

Smaller repos 553, 7%

landmark-attention 427, 5%disco 191, 2%federated-learning-public-code 161, 2%powersgd 152, 2%collaborative-attention 152, 2%dynamic-sparse-flash-attention 152, 2%llm-baselines 120, 1%schedules-and-scaling 94, 1%DenseFormer 84, 1%ChocoSGD 74, 1%llm-optimizer-benchmark 61, 1%sparsifiedSGD 58, 1%

Languages

Jupyter Notebook 3.8k stars, 46% · 4 repos
Python 2.4k stars, 30% · 10 repos
C++ 1.2k stars, 15% · 1 repo
TypeScript 191 stars, 2% · 1 repo

When they were made

16 repos with 50+ stars, made between 2016 and 2025

101001k10k sent2vecOptML_courseML_course

Quick stats

Next rank: +6 stars to reach #4,608
Next milestone: +26,802 stars to reach the top 1%
Public repos: 60, 16 with 50+ stars
Popular repos: 11 over 100 stars, 4 over 1k stars
Top repo: ML_course, #32,411 of all repos, 26% of stars
Smaller repos: 553 stars from repos under 50