A Blog post by Microsoft on Hugging Face
Back to Articles
Abstract Code Motivation Faster Decoding & No Custom Kernels Softmax Magnitude Constraint Beyond Softmax Constraint & Elimination of Attention Sinks Experimental Observations Discussions Construction of Differential Operation Design Ablations Miscellaneous Tianzhu Ye, Li Dong, Yutao Sun, Furu Wei
Github Link
Notion Link (for better readability)
Code
A Blog post by Ai2 on Hugging Face
Linear Attention Hybrids, Text Diffusion, Code World Models, and Small Recursive Transformers
Native and generic SKB-mode XDP are not semantic equivalents. This post publishes the harness methodology, corpus design, virtio…
TL;DR: We present Chipmunk, a training-free method to accelerate diffusion transformers with hardware-aware dynamic sparsity.…
Originally published on my blog. Cross-posted here with a canonical link. In June 2017, a...
Thanks to Dipankar Sarkar, Mike Czerwinski, Max Quimby, and Ponsubash Raj R for the detailed comments...
