Alternatives
Products that do what Nope – a Yup alternative that is 15 times smaller and 200 times faster does
- 1SU
Here's a project I've been working on for the last few months. It's a new (I think) algorithm, that allows to adjust smoothly - and in real time - how many calculations you'd like to do during inference of an LLM model. It seems that it's possible to do just 20-25% of weight multiplications instead of all of them, and still get good inference results. I implemented it to run on M1/M2/M3 GPU. The mmul approximation itself can be pushed to run 2x fast before the quality of output collapses. The inference speed is just a bit faster than Llama.cpp's, because the rest of implementation…
2024 · asciinema.org
- 2

- 3FFastComments▲111
2020 · fastcomments.com
- 4HT
Ever wanted to type as fast as those amazing hackers in the movies? now you can! just write something. Yes, i was really bored. To change writing speed: javascript:writer.speed=10;
2011 · duiker101.tk
- 5

- 6S2
2018 · github.com
- 7SSpeedsums▲64
2014 · speedsums.com
- 8UT
2016 · github.com
- 9

- 10IS
2016 · github.com
- 11AR
2017 · pleasespamthis.email
- 12PF
2014 · picsee.cc
- 13GA
2015 · github.com
- 14SH
2014 · speedsums.com
- 15TST-scroll▲21
2017 · github.com
- 16PN
2015 · namuol.github.io
- 17VS
2020 · ganymede.naeon.org
- 18AA
2014 · artiklur.com
- 19T3
2017 · github.com
- 20NP
2020 · github.com
- 21TS
2016 · github.com
- 22MC
2024 · minform.io
- 23MT
2016 · demos.samgentle.com
- 24GA
2015 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →