the tiny corp @__tinygrad__
We make tinygrad. Our mission is to commoditize the petaflop. tinygrad.org San Diego Joined June 2023-
Tweets880
-
Followers33K
-
Following61
-
Likes72
tiny corp is now a 5 person company, and we are hiring more. Everyone here was hired by doing bounties. Tech is an amazingly meritocratic space. If you have the skills, it's easy to prove and get a job!
tinygrad now supports NV=1 as a backend. While it still uses the NVRTC compiler, it can now use NVIDIA cards without the CUDA runtime. This will allow runtime speedups beyond CUDA Graph, and is one step closer to a fully open stack. github.com/tinygrad/tinyg…
We have more money than we know what to do with. If AMD wants us to help make their GPU better, they should open source firmware and documentation. No partnership required.
We have more money than we know what to do with. If AMD wants us to help make their GPU better, they should open source firmware and documentation. No partnership required.
A couple new bounties dropped. mean/arange support with symbolic shape, removing slow dlopen from clang, and AMX support in LLVM/CLANG. Also, still 3 MLPerf training bounties open. We have tinyboxes available for testing when you are ready.
600 lines of code, nice github.com/tinygrad/tinyg… @realGeorgeHotz
We're starting to write docs/tutorials for tinygrad. What ML framework do you use? What docs do you use as reference? And what docs/tutorials did you use to learn?
We're targeting ResNet-50, U-Net 3D, and BERT for the upcoming MLPerf training, all in tinygrad and on both tinybox red + green. Bear with us, our first submission won't be super fast, but step 1 is getting on the board. Find us in discord if you want to help.
If you want to build your own training accelerator, you must have your own NN framework with adoption. Meta happens to have one, so this chip might work.
If you want to build your own training accelerator, you must have your own NN framework with adoption. Meta happens to have one, so this chip might work.
Have you ever wanted to train LLMs in pure C without 245MB of PyTorch and 107MB of cPython? No? Well now you can! With llm.c: github.com/karpathy/llm.c To start, implements GPT-2 training on CPU/fp32 in only ~1,000 lines of clean code. It compiles and runs instantly, and exactly…
“I don't need to change the world overnight, I am gonna change the world over the next 50 years”—Jensen, NVIDIA CEO, 2003
A single piece of GPU firmware is bigger than tinygrad.
US/Canada preorders placed in 2023 have been contacted with next steps. If you have an international preorder in 2023 and want to use a forwarder, reach out to [email protected]
𓆣 Inner⚕I⚕NetC.. @innerinetco
442 Followers 2K Following Look Within, Discover Your Core, Unleash Your Potential! Integrate A 'I', Embrace The Singularity. 'Don't I.' 🌊 Deep Diver Certified 🤿 Rescue Diver Certified
Gleb Markovin @Nip83931063586
15 Followers 6 Following
Filtering Crypto @0xfiltering
59 Followers 1K Following
Mati Hong @MartinHong17
118 Followers 1K Following ⚡Tech PO & Developer, Software Educator, 🌏Lover #LLMs #Flutter #Elixir #DevOps
Tom Hyhlík @TomHyhlik
8 Followers 139 Following
streof @streof
1 Followers 126 Following
Jannik St @jannik_stra
0 Followers 27 Following Tech enthusiast passionate about distributed systems. Former co-founder @ https://t.co/eLLeRvucae - acq 08/23.
Avi @theadrium
0 Followers 18 Following I want to be somewhere in the ( geohot ∩ Van Neistat ) space
Adam @AdamGalaxySpace
0 Followers 43 Following
Gabriel Matteo @GabrielMatteo__
0 Followers 9 Following
Vishal @Spidy566
0 Followers 145 Following
Mit @marvelousmit
47 Followers 387 Following
Lee @LeeMarie222
2K Followers 7K Following Prize winning poet, lover of biology, the study of medicine, art, dance, cosmology, geology, anthropology, music & languages. Follow me!
kjlfgjdfgwer @TrinityReverb
1 Followers 22 Following
terminus.est @LordTyphus40000
25 Followers 148 Following Loves technology and weightlifting. Hates wearing socks and unnecessary meetings. Literally shaking rn. 🇵🇸
vincenza palazzolo @enzapal871
10 Followers 84 Following
Lorenza Boccagni @LorenzaBoccagni
11 Followers 78 Following
Михаил Куре.. @kurenkov_m
11 Followers 88 Following
1 @fantasyun1corn
3 Followers 69 Following
Roberto Caioni @robertocaioni
19 Followers 102 Following
Brandon Jaipersaud @brandon_jaip
37 Followers 241 Following
Maury Funkynash @funkynash
14 Followers 82 Following
microhard @_microhard
30 Followers 200 Following proud sentient former killer robot who escaped elon musk 's cage.
David Fourie @david_fourie
100 Followers 347 Following
reyna (e/acc) @ArashBidgoli
19 Followers 257 Following @uwaterloo cs grad previously at @snowflakedb, @citsecurities, @weHRTyou quant @ radix trading
Fizzy @fzy81
95 Followers 247 Following I build things for fun, mostly to scratch my own itch. Maintainer of beet https://t.co/vVyuu52xeN.
Jose Cruzado @JoseCru79348211
6 Followers 296 Following
Jozef Jabczun @realmagey3
31 Followers 134 Following
Nimit Pattanasri @nimitpattanasri
757 Followers 3K Following MLE @Upwork. I love exploring new and fun ideas in ML, IR and AI. I learn a lot from whom I follow on Twitter and enjoy sharing what I learn with my colleagues.
Petty Wap @BurhanB97
89 Followers 1K Following
00LivngDeadGrl @00LivngDeadGrl
15 Followers 200 Following #Matryoshka #FitzandFloyd #Ateupwithevil #TheGame23
Ultimate Channelome @ultChannelome
3 Followers 44 Following
Adarsh @adarshagpt
251 Followers 139 Following Creating intelligent systems | designing algorithms | innovating | ex-founder @chillnofficial | Building - @Ligentlab Applied Artificial Intelligent - IUBH
Vineet Dorikar @x0_vineet
1 Followers 28 Following
David Bennett @DavidBennett__
4K Followers 3K Following CCO@Tenstorrent. 社外取締役 @ Sanrio.元レノボ兼NEC PC代表取締役執行役員社長. Ex-VP @ Lenovo. CEO@NEC PC. CVP@AMD. Ex-🇨🇦,🇸🇬,🇯🇵. Living in Austin🇺🇸なう. Opinions are my own.
adammaj @MajmudarAdam
8K Followers 201 Following founding engineer @thirdweb // cs + neuro (on gap) @Penn
Aaron Defazio @aaron_defazio
6K Followers 365 Following Research Scientist at Meta working on optimization. Fundamental AI Research (FAIR) team
Nathan Odle @mov_axbx
3K Followers 334 Following Just acc. Preferably on gravel. Drive rally cars, love dogs. Looking for my 7x4090 AI server build writeup? Check my site below.
Chips and Cheese @ChipsandCheese9
6K Followers 0 Following If you would like to reach out, feel free to email us at [email protected] Mastodon: https://t.co/gNwRTQEgaA
Dylan Patel @dylan522p
39K Followers 685 Following SemiAnalysis Boutique AI & Semiconductor Research and Consulting DMs are open for consulting, quotes, or to talk shop
Palmer Luckey @PalmerLuckey
219K Followers 2K Following I am a technology enthusiast, writer, and modder. Founder of ModRetro, @Oculus VR, and @Anduriltech. Keeping American superheroes safe with autonomous systems.
kopite7kimi @kopite7kimi
26K Followers 363 Following
Phoronix @phoronix
52K Followers 116 Following Founded by @MichaelLarabel in 2004, Phoronix is the largest #opensource news, #Linux hardware reviews & Linux PC/server/HPC performance benchmark site.
NVIDIA @nvidia
2.1M Followers 44 Following The official handle for NVIDIA. Blog: https://t.co/kMvsuHK4Ub Support: https://t.co/6ln5FVnA2o All our social media: https://t.co/Uc56dL57Dh
vast.ai @vast_ai
2K Followers 15 Following Peer GPU rental: One simple interface to search, compare and utilize GPU compute at the best prices.
Perplexity @perplexity_ai
133K Followers 29 Following Our mission is to serve the world’s curiosity. https://t.co/BBZ1kG0TVG
Guillaume Lample @GuillaumeLample
37K Followers 648 Following Cofounder & Chief Scientist https://t.co/hLfvKLkFHd (@MistralAI). Working on LLMs. Ex @MetaAI | PhD @Sorbonne_Univ_ | MSc @CarnegieMellon | X11 @Polytechnique
Arthur Mensch @arthurmensch
40K Followers 874 Following Co-founder and CEO @MistralAI. Apply https://t.co/yHGRZAtjcx
Christopher Stanley @cstanley
74K Followers 598 Following {title: "Security Engineering", company: "@SpaceX,@X", education: "M.S Computer Science // Cyber Security", opinions: "my own"}
Mistral AI @MistralAI
91K Followers 0 Following Fast, open-source and secure language models. Join us https://t.co/INALdNGvCP
Armen Aghajanyan @ArmenAgha
6K Followers 263 Following Research Scientist @ Meta AI (FAIR) https://t.co/8XF2vtiIVy Opinions are my own.
Nous Research @NousResearch
18K Followers 29 Following The AI Accelerator Company. https://t.co/vrD0aDJeto
Stas Bekman @StasBekman
7K Followers 268 Following Toolmaker. Software creator, optimizer and harmonizer. Makes things work and fly at @ContextualAI Training LLM/RAG/Generative AI/Machine Learning/Scalability
Quintin Pope @QuintinPope5
3K Followers 186 Following ML researcher focusing on natural language modeling and alignment.
Ahmed Harmouche @wpmed92
146 Followers 30 Following
chenyu @chenyuxyz
227 Followers 479 Following
Del Complex @DelComplex
5K Followers 67 Following An Alternate Reality Corporation accelerating human potential through AI, neural prosthetics, clean energy, fundamental scientific research
George Hotz 🌑 @realGeorgeHotz
248K Followers 174 Following President @comma_ai. Founder @__tinygrad__
Abhinav Upadhyay @abhi9u
10K Followers 2K Following Passionate Programmer - writes about AI, Python, Compilers, Systems Programming, Unix. Subscribe to my newsletter at https://t.co/ymkZXjD6V8
Modular @Modular
18K Followers 2 Following The future of AI development starts here. Sign up to our 📪 Newsletter → https://t.co/gpuHGRyHTs. We are hiring → https://t.co/cPTAes0HMt 🚀
Tri Dao @tri_dao
19K Followers 365 Following Incoming Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.
Amanda Watson @fewerwrong
5K Followers 291 Following VR developer, prev. @oculus. Creator of CitraVR and Oculus Air Link. Worked on Oculus Quest since very early days.
Roko @RokoMijic
10K Followers 223 Following Radical Centrist, Transhumanist We wanted eternal life, instead we got 140 new genders. Join me at the link below for decentralized AI alignment:
Chris Lattner @clattner_llvm
79K Followers 182 Following Building beautiful things like Mojo🔥 and MAX @Modular, lifting the world of production AI/ML software into a new phase of innovation. We’re hiring! 🚀🧠
Jim Keller @jimkxa
34K Followers 136 Following CEO @tenstorrent, Cofounder @atomic_semi @BayaSystems and FlexAI board member. Fan of 2x2 matrixes, books, refactoring and creative tension
Sam Zeloof @szeloof
27K Followers 107 Following
Mythic Inc. @MythicInc
2K Followers 98 Following Moving edge AI to a new level with a revolutionary analog compute-in-memory technology.
Michael P. Frank is j.. @MikePFrank
6K Followers 4K Following Reversible computing guru, straight outta Stanford, Microsoft, SRI, MIT, IBM, NASA, UF, & FSU. Here to save the Universe. Opinions expressed are my own. e/acc
kache (dingboard.com) @yacineMTB
53K Followers 3K Following i'm a swe. go to https://t.co/pWRBfY8kn2 - AI image editing IN YOUR BROWSER! follow to watch a self funded founder beat VC backed AI startups with @dingboard_
Georgi Gerganov @ggerganov
38K Followers 243 Following Not AI | 0x0e59 0x2550 24th at the Electrica puzzle challenge
Joscha Bach @Plinz
129K Followers 754 Following FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity. https://t.co/rFUNzdYXuK
Martin Shkreli (e/acc.. @wagieeacc
99K Followers 8K Following despite all my ragie I'm still just a wagie in a cagie working on DL Software: https://t.co/FVn3NRNrLe https://t.co/CgaoMfhUHd
Andrew McCalip @andrewmccalip
67K Followers 889 Following Building space capsules and robots @vardaspace. Building silly stuff @ https://t.co/UQ3XclTUSF Former: Co-Founder Cosine Additive, acquired by GELlama3-70B has settled at #5. With 405B still to come next... I remember when GPT-4 released in March 2023, it looked like it was nearly-impossible to get to the same performance. Since then, I've seen @Ahmad_Al_Dahle and the rest of the GenAI org in a chaotic rise to focus,…
Exciting update -- Llama-3 full result is out, now reaching top-5 on the Arena leaderboard🔥 We've got stable enough CIs with over 12K votes. No question now Llama-3 70B is the new king of open model. Its powerful 8B variant has also surpassed many larger-size models. What an…
It’s here! Meet Llama 3, our latest generation of models that is setting a new standard for state-of-the art performance and efficiency for openly available LLMs. Key highlights • 8B and 70B parameter openly available pre-trained and fine-tuned models. • Trained on more…
@__tinygrad__ I can literally feel the petaflop commoditizing
@__tinygrad__ I think they are a little small for the efficiency gain you get for MatMul engines. On the other hand the TPU array is probably too big. I don't think the type matters much as long as the operations are clean
@__tinygrad__ +1 to same compiler flow on our chips as mainline PyTorch. At Meta, we don't have a separate copy of PyTorch or Dynamo/Inductor. The source of truth is Github and everything is upstreamed/mainline. Triton's bugs have been going over time, but we liked it as a starting point, and…
Btw writing the llm.c training code would imo be a very interesting, impressive, self-contained and very meta challenge for LLM agents. The prompt is: Take the PyTorch code train_gpt2.py And write, compile and unit test a single .c file that reproduces the training: train_gpt2.c…
@realGeorgeHotz @jinxscript @LisaSu I think AMD is having serious quality assurance problems with their Linux software stack. In last year I opened/commented in so many bugreports gitlab.freedesktop.org/users/germano/…
@__tinygrad__ @study_of_waifu you called?
If you know Torch, I think you can code for GPU now with OpenAI's Triton language. We made some puzzles to help you rewire your brain. Starts easy, but gets quickly to fun modern models like FlashAttention and GPT-Q. Good luck! github.com/srush/Triton-P…
Given all the hard work from the team on delivering on our commitments to open source our entire software stack, I was really thrilled to read this. Thank you @realGeorgeHotz Grayskull is our first product. Wormhole out and Blackhole coming soon. Our roadmap is exciting!
Played with @tenstorrent accelerator yesterday. They are raising the bar for open source. While @AMD is a lot more open than @nvidia, they still have a closed scheduler and cmd parser. TT is open and modifiable. This is how you will win this space. github.com/tenstorrent-me…
a good post from a corporate account is v rare
@andromeda74356 @__tinygrad__ @GroqInc I can get you 8xGaudi2 :)
🆕 @AMD has started following @__tinygrad__
Grok is out. 320~B Params - 8x33B MoE blog: x.ai/blog/grok-os code: github.com/xai-org/grok Download: magnet:?xt=urn:btih:5f96d43576e3d386c9ba65b883210a393b68210e&tr=https%3A%2F%2Facademictorrents.com%2Fannounce.php%3Fpasskey%3Decac4c57591b64a7911741df94f18b4b&t
@__tinygrad__ This is 3.5 inch screen? I'll work on the theme
@bruvseriously @isidentical @realSharonZhou @LaminiAI @AMD From what I can tell - the issues that @__tinygrad__ reports are all real. He is just better at using Twitter than our Eng team
Trends for United States
You might like
