Artificial Fintelligence
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
How does batching work on modern GPUs?
The first and most important optimization you can do for any modern deep learning system, generally speaking, is to implement batching. When you batch…
Mar 1
•
Finbarr Timbers
20
Share this post
How does batching work on modern GPUs?
www.artfintel.com
Copy link
Facebook
Email
Note
Other
1
January 2024
Where do LLMs spend their FLOPS?
LLM theory, with a hint of empirical work
Jan 29
•
Finbarr Timbers
26
Share this post
Where do LLMs spend their FLOPS?
www.artfintel.com
Copy link
Facebook
Email
Note
Other
1
December 2023
The evolution of the LLM API market
Before I studied machine learning, I was an Econ grad student banging out OLS problem sets (I see the OLS equation— (X’X)^-1X’y— whenever I close my…
Dec 13, 2023
•
Finbarr Timbers
24
Share this post
The evolution of the LLM API market
www.artfintel.com
Copy link
Facebook
Email
Note
Other
13
The evolution of the LLM API market
Note: if you’re coming to this post online, this is the same as the free post, I ran into issues opening this article up on Substack.
Dec 12, 2023
•
Finbarr Timbers
6
Share this post
The evolution of the LLM API market
www.artfintel.com
Copy link
Facebook
Email
Note
Other
November 2023
Transformer inference tricks
How to make your model run faster than a greased pig
Nov 23, 2023
•
Finbarr Timbers
28
Share this post
Transformer inference tricks
www.artfintel.com
Copy link
Facebook
Email
Note
Other
5
October 2023
Why do LLMs use greedy sampling?
"Greedy sampling is the worst form of sampling, except all those other forms that have been tried from time to time." - Winston Churchill, if he worked…
Oct 17, 2023
•
Finbarr Timbers
13
Share this post
Why do LLMs use greedy sampling?
www.artfintel.com
Copy link
Facebook
Email
Note
Other
4
September 2023
More on Mixture of Experts models
6 papers on different routing mechanisms
Sep 7, 2023
•
Finbarr Timbers
34
Share this post
More on Mixture of Experts models
www.artfintel.com
Copy link
Facebook
Email
Note
Other
1
August 2023
Papers I’ve read this week, Mixture of Experts edition
I read a bunch of papers about conditional routing models
Aug 4, 2023
•
Finbarr Timbers
37
Share this post
Papers I’ve read this week, Mixture of Experts edition
www.artfintel.com
Copy link
Facebook
Email
Note
Other
3
June 2023
The market for AI companies
After being laid low by a sick child turning into a sick family, I’ve got a bunch of articles in the queue, and I hope to have another one up by the end…
Jun 18, 2023
•
Finbarr Timbers
15
Share this post
The market for AI companies
www.artfintel.com
Copy link
Facebook
Email
Note
Other
1
May 2023
Efficient LLM inference
On quantization, distillation, and efficiency
May 9, 2023
•
Finbarr Timbers
17
Share this post
Efficient LLM inference
www.artfintel.com
Copy link
Facebook
Email
Note
Other
7
April 2023
Papers I’ve read this week: Image generation
A discussion of 4 seminal image generation papers
Apr 11, 2023
•
Finbarr Timbers
7
Share this post
Papers I’ve read this week: Image generation
www.artfintel.com
Copy link
Facebook
Email
Note
Other
2
March 2023
Five years of progress in GPTs
A summary of the progression of the SOTA in language models
Mar 29, 2023
•
Finbarr Timbers
21
Share this post
Five years of progress in GPTs
www.artfintel.com
Copy link
Facebook
Email
Note
Other
3
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts