Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Five Years of Tinygrad

geohot.github.io

Post reply on HN
Print view View original

31–40 of 167 posts

Re: Five Years of Tinygrad

#31

Post by piskov »

paxys wrote: post #6

Lots of words and weird analogies to say basically nothing. What is the status of the project? What can it do? What has it achieved in 5 years? But no, let's highlight how we follow the "Elon process". As a side note, whenever someone incessantly focuses on lines of code as a metric (in either direction), I immediately start to take them less seriously.

He was able to run nvidia gpu on mac via thunderbolt with tinygrad.

https://www.tomshardware.com/pc-components/gpus/tiny-corp-su...

—

Check tinygrad’s twitter account for specifics if you want to catch up on progress

Re: Five Years of Tinygrad

#32

Post by selkin »

dewey wrote: post #22
paxys wrote: post #6

Lots of words and weird analogies to say basically nothing. What is the status of the project? What can it do? What has it achieved in 5 years? But no, let's highlight how we follow the "Elon process". As a side note, whenever someone incessantly focuses on lines of code as a metric (in either direction), I immediately start to take them less seriously.

Using lines of code as a metric for productivity is bad. Using it to show how simple something is, or how a refactor removed x lines of code that doesn’t need to be maintained any more isn’t such a bad thing I’d say.

Less LOC also doesn't imply simplicity: just look at the demoscene, which often has the former but not the latter.

Re: Five Years of Tinygrad

#33

Post by piskov »

spiderfarmer wrote: post #7
pa7ch wrote: post #4

Very weird to market this as subscribing to "Elon process for software" I remember when defcon ctf would play Geohot's PlayStation rap video every year on the wall.

I hate it when ‘inspirational’ quotes are attributed to the person with the largest audience and not the people who came up with it, like in this case, the engineers at Lockheed’s Skunk Works.

You would be amazed

https://en.wikipedia.org/wiki/TRIZ

Re: Five Years of Tinygrad

#35

Post by ramesh31 »

spiderfarmer wrote: post #7
pa7ch wrote: post #4

Very weird to market this as subscribing to "Elon process for software" I remember when defcon ctf would play Geohot's PlayStation rap video every year on the wall.

I hate it when ‘inspirational’ quotes are attributed to the person with the largest audience and not the people who came up with it, like in this case, the engineers at Lockheed’s Skunk Works.

It's an apocryphal quote.

"A designer knows he has achieved perfection not when there is nothing left to add, but when there is nothing left to take away."

- Antoine de Saint-Exupéry

Re: Five Years of Tinygrad

#36

Post by geremiiah »

The risk for Tinygrad is that PyTorch will create a new backend for Inductor, plug in their AMD codegen stuff and walala, PyTorch still king. I mean, they could have easily just taken that route themselves instead of bothering with a new ML framework and AD engine. 99% of the work is just the AMD codegen part of the compiler.

Either way, super cool project and I wish them the best.

Re: Five Years of Tinygrad

#37

Post by peter_d_sherman »

>"We also have a contract with AMD to get MI350X on MLPerf for Llama 405B training."

Anything to help AMD (and potentially other GPU/NPU/IPU etc. chip makers) catch up with NVidia/CUDA is potentially worth money, potentially worth a lot of money, potentially worth up to Billion$...

Why?

If we have

a) Market worth Billion$

and

b) A competitive race in that Market...

then

c) We have VALUE in anything (product, service, ?, ???) that helps any given participant capture more of that market than their competitors...

(AMD (and the other lesser known GPU/NPU/IPU etc. chip vendors) are currently lagging behind NVidia's CUDA AI market dominance -- so anything that helps the others advance in this area should, generally speaking, be beneficial for all technology users in general, and be potentially profitable (if the correct deals could be struck!) by those that have the skills to do such assisting...)

Anyway, wishing you well in your endeavors, Tinygrad!

Re: Five Years of Tinygrad

#38

Post by ellis0n »

geremiiah wrote: post #36

The risk for Tinygrad is that PyTorch will create a new backend for Inductor, plug in their AMD codegen stuff and walala, PyTorch still king. I mean, they could have easily just taken that route themselves instead of bothering with a new ML framework and AD engine. 99% of the work is just the AMD codegen part of the compiler. Either way, super cool project and I wish them the best.

The main risk is that an LLM will rewrite itself and programmers will no longer be needed. I worked a bit with tinygrad and it looks quite amusing I managed to run it right away and make fixes in one of the tasks, but I decided not to commit because I was afraid of rejection. For example, the tasks are strange: $500 for two months, optimizing H.265, something that only a small group of people in the world can do.

The SV is a unique place where you can meet Geo and get $5M, maintain a bunch of hardware, build a framework in 20,000 LOC and everything works well.

Re: Five Years of Tinygrad

#39

Post by tucnak »

zephen wrote: post #12
deburo wrote: post #5

So this is all python? I bet Chris Lattner probably approached them.

Lattner is a smart guy, but I think Mojo might be the wrong direction. Time will tell. History has not so far been kind to projects which attempt to supplant cPython, whether they are other Python variants such as PyPy, or other languages such as julia. Python has a lot of detractors, but (despite some huge missteps with the 2-3 transition) the core team keeps churning out stuff that people want to use. Mojo is being…

Honestly, I feel like Julia might as well beat Mojo or sommat to the punch, sooner or later. It has some facilities and supporting infrastructure for a lot of scientific and data-handling tasks surrounding ML, if not for compiling and dispatching kernels (where XLA reins supreme to anything in the CUDA ecosystem!) For example, Bayesian programming like Turing.jl is virtually unmatched in Python. It's been a while since I looked at Lux.jl for XLA integration, but I reckon it could be incredibly useful. As long as LLM's and RLVR training thereof should continue to improve, we may be able to translate loads of exiting Pytorch code eventually.

Re: Five Years of Tinygrad

#40

Post by semiquaver »

Is this the guy who talked a big game about all the things he was going to fix at Twitter, then utterly failed when confronted with a real world codebase and gave up having done nothing of use?
Post reply on HN