Kosseila (CloudDude)

vLLM for beginners: Deployment Options (PartIII) - Cloudthrill In this final part, we’ll shift from theory to practice, covering how to deploy vLLM across different environments, from source builds to docker containers. In this series, we aim to provide a solid foundation of vLLM core concepts to help you understand how it works and why it’s emerging as a de facto choice for LLM deployment.

🚀#BlogSeries #vllm🔥
𝐯𝐋𝐋𝐌 𝐟𝐨𝐫 𝐁𝐞𝐠𝐢𝐧𝐧𝐞𝐫𝐬 𝐏𝐚𝐫𝐭 𝟑:📖 𝐃𝐞𝐩𝐥𝐨𝐲𝐦𝐞𝐧𝐭 𝐎𝐩𝐭𝐢𝐨𝐧𝐬
Learn to deploy #vLLM everywhere! Even on CPU🤫

✅Platform & model Support Matrix
✅Install on GPU & CPU
✅Build Wheel from scratch | Python vLLM package
✅Docker/Kubernetes Deployment
✅Running vLLM server (Offline + Online inference)

Zero to Civo: Deploy Talos Kubernetes with Terraform (incl Grafana & Prometheus) - Cloudthrill Today we’ll show you how to deploy an end-to-end Kubernetes cluster on a Civo Cloud with terraform . You’ll learn how to build and automate a cluster with Traefik, cert manager , letsencrypt issuer, Grafana , Prometheus.

#NewBlog from 𝐙𝐞𝐫𝐨 𝐭𝐨 @CivoCloud 🚀
💎Deploy your full fledged Talos 𝐊𝐮𝐛𝐞𝐫𝐧𝐞𝐭𝐞𝐬 stack with Terraform in one command.
check it out👉: tinyurl.com/CivoK8stf
✅ Includes Grafana, Prometheus, Let's Encrypt & more
📖 My Repo: tinyurl.com/k8sCivoRepo
#Civo #Grafana #Terraform #Kubernetes #Tutorial

YouTube video by CloudDude 🔴TechBeats live : LLM Quantization "vLLM vs. Ollama"

🎙️ Join our 🔴𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐋𝐢𝐯𝐞 Show!
🗓️ Thursday 17th 11:30 AM EDT
🎯 A chill livestream unpacking LLM #Quantization: #vllm vs #ollama. Learn about the What & How.

🔥Dope guest stars:
#bartowski from arcee.ai & Eldar Kurtic from #RedHat

🔗Stream on YouTube & Linkedin:
www.youtube.com/watch?v=XTE0...

vLLM for beginners: Key Features & Performance Optimization(PartII) - Cloudthrill In this series, we aim to provide a solid foundation of vLLM core concepts to help you understand how it works and why it’s emerging as a defacto choice for LLM deployment.

🚀#NewBlog #vllm🔥
𝐯𝐋𝐋𝐌 𝐟𝐨𝐫 𝐁𝐞𝐠𝐢𝐧𝐧𝐞𝐫𝐬 𝐏𝐚𝐫𝐭 𝟐:📖𝐊𝐞𝐲 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬 & 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧s
💎 What makes #vLLM the Rolls Royce of inference?
👉check it out: cloudthrill.ca/what-is-vllm...

✅ #PagedAttention #PrefixCaching #ChunkedPrefill
✅ #SpeculativeDecoding #FlashAttention #lmcache
✅ Tensor & #PipelineParallelism⚡

Terraform Pipelines for Dummies Part3: GitHub Actions Azure Deploy with OIDC - Cloudthrill Struggling with Azure credential management in your CI/CD pipelines? Both Azure and GitHub Actions now support OpenID Connect (OIDC) for secure deployments by simplifying the process, and aligning with modern security practices. With GitHub’s OIDC provider, you can authenticate directly from your workflows using managed identities without the need for static access keys.

🚀#NewBlog 𝐆𝐢𝐭𝐇𝐮𝐛 actions Azure deploy with 𝐎𝐈𝐃𝐂!
💡Over 𝟐𝟑 𝐦𝐢𝐥𝐥𝐢𝐨𝐧𝐬 secrets were exposed in #GitHub last year💀 & 𝟓𝟎K+ #Huggingface tokens leaks every month!
🛡️Switch to 𝐬𝐞𝐜𝐫𝐞𝐭𝐥𝐞𝐬𝐬 with Pipeline identity now!
👉We show you how: cloudthrill.ca/github-actio...
#Azure #NHI #CICD #Terraform #ManagedIdentity

vLLM for beginners: The Fundamentals - Cloudthrill In this series, we aim to provide a solid foundation of vLLM core concepts to help you understand how it works and why it’s emerging as a defacto choice for LLM deployment.

🚀#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

✅ What is vLLM ( vLLM vs Ollama)
✅ Core Architecture (Engine, Sched, Execution, Memory)
✅ Offline and Online inference

Ep06: "GitHub Security horror stories " (with Steve Giguere) Tech Beats Unplugged · Episode

🎙𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐔𝐧𝐩𝐥𝐮𝐠𝐠𝐞𝐝 is BACK #Episode 06 !!!👊🏻
🎧🔥"𝐆𝐢𝐭𝐇𝐮𝐛 𝐒𝐞𝐜𝐮𝐫𝐢𝐭𝐲 𝐡𝐨𝐫𝐫𝐨𝐫 𝐬𝐭𝐨𝐫𝐢𝐞𝐬 with
#SteveGiguere "☢️...tons of 𝐚𝐭𝐭𝐚𝐜𝐤 𝐯𝐞𝐜𝐭𝐨𝐫𝐬, best practices, and a lot of laughs😅. You don't wanna miss this !
Thank you Steve🙏🏻
👉🏻 spoti.fi/4dYicES 👈🏻

🎙️𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐔𝐧𝐩𝐥𝐮𝐠𝐠𝐞𝐝 is back! new episode drops tomorrow!🔥👀Mystery guest. Bold truths. Shocking discoveries you’re not ready to hear😱 🎧Mics are hot, truths are hotter. Stay tunned !!😎
#TechPodcast #GitSecStory

#NewBlog 𝐊𝐕 𝗖𝗮𝗰𝗵𝗲 𝗘𝘅𝗽𝗹𝗮𝗶𝗻𝗲𝗱: like I'm 5😎
🧠Ever wondered what #KVCache really is in LLM inference? Forget the math-heavy blabla—this one's made to click !
👉check it out: cloudthrill.ca/kv_cache-exp...
@Cloud_Thrill
#vLLM #AIInfra #lmcache

🧠First thing to do when using Jules from google and connecting your GitHub..! #GoogleJules

HashiCorp Vault for Dummies: Setup your 1st Vault with TLS (WSL) - Cloudthrill n this guide, you'll learn how to set up a local Vault server using Raft storage and TLS in a WSL (Windows Subsystem for Linux) environment. Whether you're just starting with secrets management, prepp...

🚀 #NewBlogAlert 🛡️ #HashiCorpVault
I'm kicking off a 𝐕𝐚𝐮𝐥𝐭 𝐟𝐨𝐫 𝐃𝐮𝐦𝐦𝐢𝐞𝐬 𝐬𝐞𝐫𝐢𝐞𝐬 with
𝐏𝐚𝐫𝐭 𝟏:🔐 𝐇𝐨𝐰 𝐭𝐨 𝐒𝐞𝐭 𝐔𝐩 𝐇𝐚𝐬𝐡𝐢𝐂𝐨𝐫𝐩 𝐕𝐚𝐮𝐥𝐭 with 𝐑𝐚𝐟𝐭 & 𝐓𝐋𝐒
👉check it out: tinyurl.com/HashiVault-f...
@cloudthrill.bsky.social

Explore OCI DevOps: Pipeline your Terraform Stack from GitHub to OCI Event posted by about Explore OCI DevOps: Pipeline your Terraform Stack from GitHub to OCI on AIOUG.

🚨Catch me live at @AIOUG tomorrow!😎
Pumped to join India Oracle Users Group for a live session #OCIDevOps #Terraform
🗓️ May 16 | 🕗 8:30 AM EST / 6:00 PM IST
Save your spot: aioug.org/events/explo...

History Doesn't Repeat Itself, but It Often Rhymes...

Exciting news for my team at @cloudthrill.bsky.social !♥️we're officially accepted into the 𝐈𝐍𝐕𝐈𝐃𝐈𝐀 𝐈𝐧𝐜𝐞𝐩𝐭𝐢𝐨𝐧 𝐏𝐫𝐨𝐠𝐫𝐚𝐦

YouTube video by CloudDude Kelsey Hightower: Why Black Founders still struggle in Silicon valley? (ep03)

🎙️In 𝐄𝐩𝟎𝟑, I sat down with @kelseyhightower.com to unpack a tough truth and he kept it 💯
➡️With only 𝟏.𝟐% of VC funding, 𝐖𝐡𝐲 𝐁𝐥𝐚𝐜𝐤 𝐅𝐨𝐮𝐧𝐝𝐞𝐫𝐬 𝐬𝐭𝐢𝐥𝐥 𝐬𝐭𝐫𝐮𝐠𝐠𝐥𝐞 𝐢𝐧 𝐒𝐢𝐥𝐢𝐜𝐨𝐧 𝐕𝐚𝐥𝐥𝐞𝐲?
📺listen to the full take here: youtu.be/gsMjYZZOBe0 #TechBeatsUnplugged #NumbersDonLie✊🏾

TAICO May 2025 meetup!, Wed, May 7, 2025, 5:30 PM | Meetup The TAICO team is proud to announce our next meetup at the Adaptavist office in Toronto. Much thanks to [Adaptavist](https://www.adaptavist.com/ "https://www.adaptavist.com

🚨#AI & #CyberSec heads in #Toronto!
Join us on Wednesday, 𝐌𝐚𝐲 𝟕𝐭𝐡 from 5:30pm-8pm EST for another exciting #TAICO Meetup (Toronto AI and Cybersecurity Organization).
#Cloudthrill #ProudSponsor🔥
www.meetup.com/taico-toront...

YouTube video by CloudDude Meta announced 𝐌𝐞𝐭𝐚 𝐀𝐏𝐈, SDKs with inference platform (race for cost trimming)

🔵Meta announced 𝐌𝐞𝐭𝐚 𝐀𝐏𝐈, SDKs with inference, eval/ tuning platform.. officially Joining AI API business ... But Size always matters according to @databricksinc.bsky.social CEO's Ali ghodsi
youtu.be/mGtQLBPw4iU?...
#AI #Inference #TokenCost #llamaCon #llama🦙

Reality Check I'm sick and god-damn tired of this! I have written tens of thousands of words about this and still, to this day, people are babbling about the "AI revolution" as the sky rains blood and crevices open...

Newsletter: I am sick and god damn tired of everybody pretending that generative AI is the next big thing. The media is complicit in accepting fantastical nonsense - both in the numbers put out by OpenAI and the silly jobs created by Anthropic - and it has to stop.
www.wheresyoured.at/reality-check/

How to pass the CKA certification - Cloudthrill CKA is 100% hands-on—no multiple-choice, just real-world challenges. In this post, I’ll break down:✅ Exam structure & key domains✅ How I prepared (resources, labs, and time investment)✅ Tips to ace it...

#NewBlog 𝐇𝐨𝐰 𝐭𝐨 𝐏𝐚𝐬𝐬 𝐭𝐡𝐞 𝐂𝐊𝐀 𝐂𝐞𝐫𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧 – 𝐍𝐨 𝐑𝐞𝐭𝐚𝐤𝐞𝐬!🚀
Time to refocus on your goals—like finally crushing that elusive 𝐂𝐊𝐀 𝐞𝐱𝐚𝐦 with my curated guide on:
✅ Best resources, hands-on labs, time investment tips
✅ D-day strategies, CLI tricks that save you time
🔥Just Do it💪
👉🏻 buff.ly/S60cXwN #CNCF

I know. Europe will also apply the same for north americans (ETIAS). It just didn't sound logical to see labor laws applied on travelers working remotely for foreign companies on a short stay (couple weeks).

It's like when ICE ruled to deport someone but then denied bail because of a flight risk;)

I can read the word ESTA, still can't help but ask if this applies to non-citizens (rhetorical).

YouTube video by Wiz CISO MUSICAL | Official Broadway Trailer

$32B for this!... youtu.be/4W17F9Ho_38?...

🧠 𝐆𝐏𝐓 𝐌𝐨𝐝𝐞𝐥𝐬 𝐟𝐨𝐫 𝐝𝐮𝐦𝐦𝐢𝐞𝐬 #cheatsheet
🤔 If you’ve opened #ChatGPT lately and thought:
“𝐖𝐚𝐢𝐭… 𝐰𝐡𝐚𝐭’𝐬 𝐨𝟑? 𝐀𝐧𝐝 𝐰𝐡𝐲 𝐚𝐫𝐞 𝐭𝐡𝐞𝐫𝐞 𝐬𝐨 𝐦𝐚𝐧𝐲 𝐦𝐨𝐝𝐞𝐥𝐬 𝐧𝐨𝐰?” You’re not alone. Today #openAI finally answered🙋🏻‍♀️
👉🏻https://platform.openai.com/docs/models/compare

Turn Your Localhost into a FREE Public URL with Ngrok & Zrok -part 1 - Cloudthrill Ngrok VS Zrok allow you to securely expose your local services to the internet. Plus, they provide free static domains—no extra configuration needed. Let’s dive in!

🚀#NewBlogpost 𝐍𝐨 𝐏𝐮𝐛𝐥𝐢𝐜 𝐈𝐏? 𝐍𝐨 𝐏𝐫𝐨𝐛𝐥𝐞𝐦!
Turn Your 𝐋𝐨𝐜𝐚𝐥𝐡𝐨𝐬𝐭t into a FREE public URL
with 𝐙𝐫𝐨𝐤 from @openziti!— This 𝐙𝐞𝐫𝐨𝐓𝐫𝐮𝐬𝐭 tool allows you to securely expose your local apps to the internet for FREE! 🔄 👉 cloudthrill.ca/ngrok-vs-zrok-part1

This is not the revolution I expected from AI ...;) #AIEntitlement

🔥Super pumped to speak about AI inference in OKE, See you next Wednesday (April 2th)! RSVP below👇🏻

258,341 students... Go be a consultant they said 🥹🥲🥹