Article
No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL
- +4
toslali-ibm, mirinflim, qgallouedec, esnible, rganti, mudhakar
• • 105
nekocyrene
nekocyrene
AI & ML interests
An AI & ML Researcher, develops innovative artificial intelligence solutions, designing algorithms and models.
Recent Activity
upvoted an article 7 days ago
No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL upvoted a paper 8 days ago
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open
Language ModelsOrganizations
None yet
upvoted an article 7 days ago
upvoted a paper 8 days ago
upvoted an article 8 days ago
Article
🐯 Liger GRPO meets TRL
- +4
shisahni, kashif, smohammadi, ShirinYamani, m0m0chen, liberty4321
• • 55 upvoted a collection 17 days ago
upvoted a paper 19 days ago
upvoted an article 23 days ago
Article
The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
codelion
• • 67 upvoted an article 4 months ago
Article
混合专家模型（MoE）详解
- +4
osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq
• • 99 upvoted 4
papers 4 months ago
Muon is Scalable for LLM Training
Paper • 2502.16982 • Published • 17
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 464
Textbooks Are All You Need
Paper • 2306.11644 • Published • 159
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
Paper • 2506.05209 • Published • 66
upvoted an article 4 months ago
Article
Beyond LoRA: Can you beat the most popular fine-tuning technique?
- +2
BenjaminB, sayakpaul, hubnemo, kashif
• • 105 upvoted an article 5 months ago
Article
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
LinkedIn
• • 82