Article
Ulysses Sequence Parallelism: Training with Million-Token Contexts
•
24
yyx
RuggingHace
AI & ML interests
None yet
Recent Activity
new activity 9 days ago
facebook/layerskip-llama2-13B:layerskip-llama2-13B access denied upvoted an article 11 days ago
Ulysses Sequence Parallelism: Training with Million-Token Contexts upvoted an article 11 days ago
Keep the Tokens Flowing: Lessons from 16 Open-Source RL LibrariesOrganizations
None yet
upvoted 2
articles 11 days ago
Article
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
- +7
•
79
upvoted an article about 1 month ago
Article
Custom Kernels for All from Codex and Claude
- +2
•
72
upvoted 2
articles about 2 months ago
Article
Training Design for Text-to-Image Models: Lessons from Ablations
•
69
Article
Text-to-image Architectural Experiments
•
55
upvoted a paper about 2 months ago
upvoted an article about 2 months ago
Article
Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek
•
45
upvoted an article 2 months ago
Article
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
•
67
upvoted 2
articles 5 months ago
Article
You could have designed state of the art positional encoding
•
455
Article
What is test-time compute and how to scale it?
•
117
upvoted 2
articles 7 months ago
Article
Make your ZeroGPU Spaces go brrr with ahead-of-time compilation
- +2
•
77
Article
From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels
•
95
upvoted an article 9 months ago
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
•
767