lexpank

// Nobody asked for microgpt in CUDA C, which is exactly why it had to happen.
// It is no longer particularly micro.
// It is, however, stupidly fast.

#include <cuda_runtime.h>
#include <cublas_v2.h>

#include <math.h>
#include <stdio.h>
#include <stdlib.h>

karpathy

"""
The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.

@karpathy
"""

import os       # os.path.exists
import math     # math.log, math.exp