Kosseila (CloudDude) ☁️📡🍉
@CloudDude_
Founder @cloud_thrill | Speaker | MultiCloud | local AI | Beatmaker 🎙Podcast: https://bit.ly/Techbeats
🎙𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐔𝐧𝐩𝐥𝐮𝐠𝐠𝐞𝐝 is BACK #Episode 06 !!!👊🏻 🎧🔥"𝐆𝐢𝐭𝐇𝐮𝐛 𝐒𝐞𝐜𝐮𝐫𝐢𝐭𝐲 𝐡𝐨𝐫𝐫𝐨𝐫 𝐬𝐭𝐨𝐫𝐢𝐞𝐬 with @_SteveGiguere_ "☢️tons of 𝐚𝐭𝐭𝐚𝐜𝐤 𝐯𝐞𝐜𝐭𝐨𝐫𝐬, best practices, and a lot of laughs😅...Thank you Steve🙏🏻 👉🏻 spoti.fi/4dYicES 👈🏻
“The more you trust AI, the less you should trust it.” - Joe Hellerstein, Professor at UC Berkeley
ouch .. After Meta broke ground on a $750 million data center on the edge of Newton County, Ga., the water taps in Beverly and Jeff Morris’s home went dry. Within a year, water pressure had slowed to a trickle. Soon, none came out of bath & kitchen taps. archive.is/iMdS3

Want to finally get 𝐪𝐮𝐚𝐧𝐭𝐢𝐳𝐚𝐭𝐢𝐨𝐧? vLLM vs Llama.cpp? Catch the replay of this dope stream with #Bartowski & Eldar Kurtic— we break it all down: ⚔️ GGUF GPTQ AWQ Tradeoffs 📊 Benchmarks/evals/edge AI 🧠 When to use what... The Future 😱 🔴 Watch the replay 👇🏼
🎙️ Join our🔴𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐋𝐢𝐯𝐞 Show! 🗓️ Thursday 17th 11:30 AM EDT 🎯 A chill livestream unpacking LLM #Quantization: @vllm_project vs @ollama the What & How. 🔥Dope guest stars: @bartowski1182 & @_EldarKurtic 🔗Stream on YouTube & Twitter: youtube.com/watch?v=XTE0oS…
Want to finally get 𝐪𝐮𝐚𝐧𝐭𝐢𝐳𝐚𝐭𝐢𝐨𝐧? vLLM vs Llama.cpp? Catch the replay of this dope stream with #bartowski & Eldar kurtic — we break it all down: ⚔️ GGUF GPTQ AWQ Tradeoffs 📊 Benchmarks/evals/edge AI 🧠 When to use what... The Future 😱 🔴 Watch the replay 👇🏼
🎙️ Join our🔴𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐋𝐢𝐯𝐞 Show! 🗓️ Thursday 17th 11:30 AM EDT 🎯 A chill livestream unpacking LLM #Quantization: @vllm_project vs @ollama the What & How. 🔥Dope guest stars: @bartowski1182 & @_EldarKurtic 🔗Stream on YouTube & Twitter: youtube.com/watch?v=XTE0oS…
🎙️ Join our🔴𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐋𝐢𝐯𝐞 Show! 🗓️ Thursday 17th 11:30 AM EDT 🎯 A chill livestream unpacking LLM #Quantization: @vllm_project vs @ollama the What & How. 🔥Dope guest stars: @bartowski1182 & @_EldarKurtic 🔗Stream on YouTube & Twitter: youtube.com/watch?v=XTE0oS…
🚀#NewBlog @vllm_project 🔥 𝐯𝐋𝐋𝐌 𝐟𝐨𝐫 𝐁𝐞𝐠𝐢𝐧𝐧𝐞𝐫𝐬 𝐏𝐚𝐫𝐭 𝟐:📖𝐊𝐞𝐲 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬 & 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧s💫 💎 What makes #vLLM the Rolls Royce of inference? 👉check it out: cloudthrill.ca/what-is-vllm-f… @vllm_project @lmcache #LLMPerformance
What if you used diffusion models to answer your prompts. That's what @GoogleDeepMind just released! I just tried it and it's insanely fast (up to 𝟐𝟎𝟎𝟎𝐭𝐤/𝐬)😱 join the wait-list 😉 deepmind.google/models/gemini-… #GeminiDiffusion #DeepMind #AI #DiffusionModels #AIResearch

The single greatest change in my life came from doing one thing: Ignoring people’s advice who didn't have what I wanted. This includes parents, friends, acquaintances, and random posts I see on my newsfeed. The world got quieter, and that made decisions a lot easier.
Here we go @Visa CEO just dropped THE stable-coins pitch. Pay in coins using your VISA card globally 🌎 Cash has a new look✨💵
🚀#NewBlog GitHubactions Azure deploy with 𝐎𝐈𝐃𝐂! 💡Over 𝟐𝟑 𝐦𝐢𝐥𝐥𝐢𝐨𝐧𝐬 secrets were exposed in @GitHub last year💀𝟓𝟎K+ @huggingface tokens leaks/month! 🛡️Switch to 𝐬𝐞𝐜𝐫𝐞𝐭𝐥𝐞𝐬𝐬 with OIDC now! 👉We show you how: cloudthrill.ca/github-actions… #Azure #NHI #CICD #Terra
Wrapper of a wrapper of a wrapper...
I reverse engineered @cluely – and their desktop source code exposes their entire system prompts and models used. What's inside? 🧵
🚀#NewBlogAlert " What is #vLLM ?" We’re kicking off our 𝐯𝐋𝐋𝐌 𝐟𝐨𝐫 𝐁𝐞𝐠𝐢𝐧𝐧𝐞𝐫𝐬 𝐬𝐞𝐫𝐢𝐞𝐬 with 𝐏𝐚𝐫𝐭 𝟏:📖 𝐓𝐡𝐞 𝐅𝐮𝐧𝐝𝐚𝐦𝐞𝐧𝐭𝐚𝐥𝐬💫 New to vLLM? This one's for you👇🏻: cloudthrill.ca/what-is-vllm @vllm_project @lmcache #CoreArchitecture #OfflinevsOnline