Alexandre Boucaud aboucaud

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

High-Performance Matrix Multiplication

This is a short post that explains how to write a high-performance matrix multiplication program on modern processors. In this tutorial I will use a single core of the Skylake-client CPU with AVX2, but the principles in this post also apply to other processors with different instruction sets (such as AVX512).

Intro

Matrix multiplication is a mathematical operation that defines the product of

pretty_csv/pretty_tsv

These are some simple bash functions and scripts for making CSV/TSV files prettier on the command line

see http://stefaanlippens.net/pretty-csv.html for more information.

	#!/bin/bash
	##############################################################################################################################
	# USAGE: sbatch myscript.sh <RUN_NAME> python <script.py> [args...]
	# EXAMPLE: sbatch myscript.sh my_experiment_v1 python train.py --lr 0.01
	##############################################################################################################################
	#SBATCH --job-name=Likelihoods
	#SBATCH --cpus-per-task=8
	#SBATCH --nodes=1
	#SBATCH --tasks-per-node=1
	#SBATCH --hint=nomultithread

	[Unit]
	Description=Set NVIDIA power limit above default

	[Service]
	Type=oneshot
	ExecStartPre=/usr/bin/nvidia-smi -pm 1
	ExecStart=/usr/bin/nvidia-smi -pl 275

	#!/usr/bin/awk -f

	# This program is a copy of guff, a plot device. https://github.com/silentbicycle/guff
	# My copy here is written in awk instead of C, has no compelling benefit.
	# Public domain. @thingskatedid

	# Run as awk -v x=xyz ... or env variables for stuff?
	# Assumptions: the data is evenly spaced along the x-axis

	# TODO: moving average