Posts
-
Explaining some llm-d benchmarking data
-
Back-of-the-envelope comparison of expert parallelism in llm-d
-
Symmetric Matrix Block Inverse
-
Some Notes on dragonfly (bayesian optimization)
-
Organizations and Groups Using Data/ML for Conservation
-
Using Toy Examples to Understand Simple Neural Networks
-
An Interesting Integral
-
A Detailed Look at Backpropagation in Feedforward Neural Networks
-
A Physicist's Proof of the Central Limit Theorem
subscribe via RSS