SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
Paper • 2512.14080 • Published • 10
Nguyễn Sỹ Trọng
trongg
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
trongg/Qwen3.6-8B-A1.4B published a model 3 days ago
trongg/Qwen3.6-8B-A1.4B upvoted a paper 4 days ago
SonicMoE: Accelerating MoE with IO and Tile-aware OptimizationsOrganizations
upvoted a paper 4 days ago
upvoted an article 5 months ago
Article
Accelerate Large Model Training using DeepSpeed
smangrul, sgugger
• • 7 upvoted an article 6 months ago
Article
Context Parallelism
huseinzol05
• • 32 upvoted an article 11 months ago
Article
From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
- +2
mirinflim, aldopareja, muellerzr, stas
• • 62 upvoted 2
articles 12 months ago
Article
🤗 PEFT welcomes new merging methods
smangrul, sayakpaul
• • 30 Article
Merge Large Language Models with mergekit
mlabonne
• • 157 upvoted a paper over 1 year ago