Hi everyone, @icpp and I have been talking and thought it would be great to have a Technical Working Group around DeAI where we can e.g. exchange ideas, initiatives and updates on relevant IC features. So we’re reaching out with this post to get your feedback on this idea; Who would be interested in…

[image] Alexander Long @AlexanderJLong So crazy to me that 6 months ago literally everyone serious AI researcher I talked to told me stuff like this wasn't feasible. Decentralized Training is gonna work - we're still at DDP stage and there's a long way to go for giant model runs, but no …

Hi everyone, thank you for today’s call (2024.09.05). This is the generated summary (short version, please find the long version here ): In today’s DeAI Working Group call for the Internet Computer, discussions centered on AI development with a focus on large language models (LLMs), vector databases…

[image] Decentralized Training Looms Collaborative Training of foundation models is closer to actualization than broadly understood. The popular view that low bandwidth node-to-node connections render this infeasible is incorrect.

Hi everyone, thank you for today’s call (2024.09.26). This is the generated summary (short version, please find the long version here ): Today’s DeAI Working Group call for the Internet Computer focused on potential Delta V integrations, new participant introductions, and plans to publish a DeAI ma…

Hi everyone, thank you for today’s call (2024.10.03). This is the generated summary (short version, please find the long version here ): In today’s DeAI Working Group call, participants discussed the challenges of implementing shared stable storage for canisters to avoid re-uploading large AI model…

Anyone faced similar issue while working on deep learning or have a sample for dividing work into multiple messages? [image] Divided Message yet still receiving "Canister exceeded the limit" after few rounds Developers Divided a long run into chunks, and first few runs go…

Hi All, cross-posting here for awareness. Looking forward to feedback on this pre-release of ICGPT with a llama.cpp backend. [image] Llama.cpp on the Internet Computer Programs & Applications It’s been a journey, but a pre-release of ICGPT with a llama.cpp backend is now…

I’m getting the following error using TintStories: ERROR: The canister TinyStories-42M-Raw LLM is not ready... …and this with the llama.cpp: As an AI assistant, I’m here to provide information and answer questions related to information technology and technology. I am here to assist you in a var…

Hi @paulous , thank you for trying it out. Another user reported the error with the TinyStories canister. It works OK for most users, but some get this error. Not sure yet why, but looking into it. Can you tell me a bit more detail about your test environment. Are you trying it out on laptop or mo…

my pleasure :slightly_smiling_face: i was using arch based pc and brave, all up to date. sounds like fascinating work.

Technical Working Group DeAI

Developers

ktimam October 11, 2024, 12:30pm 203

Anyone faced similar issue while working on deep learning or have a sample for dividing work into multiple messages?

Topic		Replies	Views
AI and machine learning on the IC? Developers	114	11295	June 20, 2024
DeAI.chat – Decentralized AI chat on the Internet Computer Showcase DeAI	0	278	February 25, 2025
Llama2.c LLM running in a canister! Programs & Applications	61	5720	July 1, 2024
funnAI: first Proof‑of‑AI‑Work on ICP Showcase	18	1740	July 2, 2026
Technical Working Group: Scalability & Performance Developers Discussing , community-consideration	180	11102	October 16, 2025

Technical Working Group DeAI

Related topics