[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
▼ Settings Mobile Home
/g/ - Technology

Name
Options
Comment
Verification
4chan Pass users can bypass this verification. [Learn More] [Login]
File
  • Please read the Rules and FAQ before posting.
  • You may highlight syntax and preserve whitespace by using [code] tags.

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]


[Advertise on 4chan]


AI compression is the future
>>
>>110393872
why does it take a week, do they read 100mb a trillion times
>>
>>110393872
>a week
lol
>>
>>110393882
It likely just trains a tiny LLM to the point where it's so fried it can only reproduce the training data 1:1 and nothing else.
>>
Wow, since the AI stocks are crashing, the catalogue have been spammed nonstop with even more shills.
Noooooticing.
>>
>>110393882
>>110393911
GPUs are built to crunch shaders really fast that's it. They suck at general purpose stuff suited to a CPU. That's why AV1 on GPU looks like ass compared to DAV1D.
>>
>"A dozen hybrid compressors can beat its score, but none relies on a neural network alone"
So this is just pure AI wank with little practical purpose
>>
>>110393931
Your 401k depends on that AI wank
>>
>>110393872
Can I extract an arbitrary page and read it though?
>>
>>110393872
Reminds me of the guy that "compressed images" reducing them to a prompt.
>>
>>110393872
i cant wait for the 5MB 1080p rip of The Odyssey where i wait 3 weeks to decompress before playback
>>
File: 1754216949522.png (451 KB, 666x679)
451 KB PNG
>>110393872
futazip?
>>
I have a better algorithm
>compression process: delete the data
>decompression process: wait for the universe to give rise to the circumstances that will produce an exact copy of the input data
>>
>>110393939
yes it will be ready in about a week
>>
>>110393882
>do they read 100mb a trillion times
You jest but that is literally how transformers work. All weights are read for each token generated (mixture of experts changes this but a 100mb model is probably dense).
>>
File: 1795103718139320.png (269 KB, 2514x2298)
269 KB PNG
>>
>>110393872
rar stocks are crashing
thanks a lot nvidia
>>
>week per direction with 2x 1000W TDP gpus
truly magical and efficient
>>
yeah this was proposed in like 2023, before people realized how fucking expensive and slow itd be
unfortunately the AI scene is now full of dumb cunts so theyre trying it again
>>
Why don't they just make it into a text file
>>
File: 1794605142363169.gif (371 KB, 640x352)
371 KB GIF
>>110393922
>>
>>110393872
>TuFa zip
>FuTa zip
>>
>>110393872
wikipedia is mostly text, zip can already do that in a few seconds
>>
>>110393872
Compression & communication are outdated technologies. Instead train your computer to already know everything without needing input
>>
>>110393872
seems kinda excessive. can't they make a model that's 20x faster with 2-3x worse compression ratio that actually has a practical usecase?
>>
>>110393926
b200 is not for shaders but for matmul it doesn't even have display out ports
>>
>>110393872
>compress
>wikipedia
how much shit can you fit in a 5lb bag
>>
>>110394514
this is not meant as a viable product for people to use.
>"A dozen hybrid compressors can beat its score, but none relies on a neural network alone"
It's like trying to get the highest score while restricting yourself to some specific tool in a vidya. Just to see how it goes.
>>
>>110393882
the 100mb is the llm, it takes a week bc its bruteforcing the wiki based on its sha
>>
>hey guys check out my new compression NisPe.zip!
>>
>>110393872
You laugh, but when shit hits the fan and all you have left is on your person a 128MB flash drive and two Nvidia B200 GPUs and 400kWh of power, you'll be wishing you had just compressed it. At least I'll be prepared. Maybe if you agree to be my concubine I'll lend you a little knowledge.
>>
File: laughing autismo.gif (502 KB, 500x281)
502 KB GIF
>>110393872
> a week
>>
>>110393986
Mambo futa...
>>
>>110393926
What? GPU encoders are fixed function units, all the shaders do is scaling and maybe noise removal. There are commercial encoders that do use the GPU cores but they are way slower.



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.