Akash Singh
akashicmarga
AI & ML interests
Conversational AI
Recent Activity
liked
a Space 1 day ago
lm-provers/qed-nano-blogpost upvoted an article 17 days ago
Prefill and Decode for Concurrent Requests - Optimizing LLM Performance upvoted an article 17 days ago
Continuous batching from first principles Organizations
-
Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
Paper • 2312.03694 • Published • 2 -
FaceStudio: Put Your Face Everywhere in Seconds
Paper • 2312.02663 • Published • 32 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 189
-
Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
Paper • 2312.03694 • Published • 2 -
FaceStudio: Put Your Face Everywhere in Seconds
Paper • 2312.02663 • Published • 32 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 189
datasets 0
None public yet