Learn finite field theory.
Learn quantum error correction.
Learn enough algebraic geometry to understand triality.
Learn quantum error correction.
Learn enough algebraic geometry to understand triality.
John Hopfield Now What 3_0.pdf
https://pni.princeton.edu/sites/g/files/toruqf321/files/documents/John%20Hopfield%20Now%20What%203_0.pdf
https://pni.princeton.edu/sites/g/files/toruqf321/files/documents/John%20Hopfield%20Now%20What%203_0.pdf
Exploring the mechanisms of action of probiotics in depression - https://doi.org/10.1016/j.jad.2025.01.153
Being able to build and understand the best way to solve a problem isn't remotely the same thing
find weak spots that exist due to coordination failures or attention scarcity, not technical difficulty
The CUDA kernel space is crowded
The Metal/MLX kernel space is EMPTY
Everyone with a MacBook wants faster local inference
Almost nobody is doing serious Metal kernel optimization
The Metal/MLX kernel space is EMPTY
Everyone with a MacBook wants faster local inference
Almost nobody is doing serious Metal kernel optimization
#todo implement paged attention kernel for mlx (decode + prefill), then build block manager (allocator + block tables + copy-on-write), wrap into paged model that swaps mlx-lm attention, finally integrate as sglang mlx runner.
paged attention is the core primitive that makes sglang useful, without it sglang on mlx is just regular inference.
paged attention is the core primitive that makes sglang useful, without it sglang on mlx is just regular inference.