Tech Beats Unplugged cover art

Tech Beats Unplugged

Tech Beats Unplugged

By: Cloud Dude
Listen for free

About this listen

 Welcome to Tech Beats Unplugged, the podcast where we dive into the dynamic world of technology, open source, cloud innovation, devops, Tech economics, and much more. Join us as we bring together experts, thought leaders, and innovators from diverse tech arenas and leading tech vendors. Here, we believe in creating a safe space where guests can freely share their opinions, insights, and experiences without any strings attached. It's a platform dedicated to unlocking knowledge, fostering meaningful discussions, and exploring the latest trends that shape the tech industry. Time to Tune in !Cloud Dude
Episodes
  • 🔴TechBeats live : LLM Quantization "vLLM vs. Llama.cpp"

    🔴TechBeats live : LLM Quantization "vLLM vs. Llama.cpp"
    Jul 19 2025

    👋🏼Hey AI heads🎙️ 𝐉𝐨𝐢𝐧 𝐮𝐬 for the very first 𝐓𝐞𝐜𝐡 𝐁𝐞𝐚𝐭𝐬 𝐋𝐢𝐯𝐞🔴, hosted by Kosseila—aka @CloudDude , From @CloudThrill. 🎯 This chill & laid back livestream will unpack 𝐋𝐋𝐌 𝐪𝐮𝐚𝐧𝐭𝐢𝐳𝐚𝐭𝐢𝐨𝐧🔥: ✅𝐖𝐇𝐘 it matters ✅𝐇𝐎𝐖 it works✅ Enterprise (vllm) vs Consumer (@Ollama) tradeoffs ✅ and 𝐖𝐇𝐄𝐑𝐄 it’s going next.We’ll be joined by two incredible guest stars to talk about 𝐄𝐧𝐭𝐞𝐫𝐩𝐫𝐢𝐬𝐞 𝐯𝐬 𝐂𝐨𝐧𝐬𝐮𝐦𝐞𝐫 quantz 🗣️:🔷 𝐄𝐥𝐝𝐚𝐫 𝐊𝐮𝐫𝐭𝐢𝐜́, bringing the enterprise perspective with vLLM.🔷𝐂𝐨𝐥𝐢𝐧 𝐊𝐞𝐚𝐥𝐭𝐲, aka Bartowski, top downloaded GGUF quant 𝐋𝐋𝐌𝐬 on Hugging Face.🫵🏼 Come learn, and have some fun😎. 𝐂𝐡𝐚𝐩𝐭𝐞𝐫𝐬 :(00:00) Host Introduction(04:07) Eldar Intro (07:33) Bartowski Intro (13:04) What's Quantization! (16:19) Why LLMs Quantization matters? (20:39) Training Vs Inference "The new deal" (27:46) Biggest misconception about quantization(33:22) Enterprise Quantization in production (vLLM)(48:48) Consumer LLMs and quantization (Ollama, llama.cpp, GGUF) "LLMs for the people"(01:06:45) Bitnet 1Bit Quantization from Microsoft (01:28:14) How long it takes to Quantize a model (llama3 70B) GGUF or lm--compressor(01:34:23) What is I-Matrix, and why people confuse it with IQ Quantization ? (01:39:36) What's LoRA and LoRAQ(01:42:36) What is Sparsity ? (01:47:42) What is Distillation ?(01:52:34) Extreme Quantization (Unsloth) of Big models (Deepseek) at 2bits with 70% size cut(01:57:27) Will future models llama5 be trained on fp4 tensor cores ? if so why quantize it?(02:02:15) The future of LLMs on edge Devices (Google AI edge)(02:08:00) How to Evaluate the quality of Quantized model ?(02:26:09) Hugging face Role in the world of LLM/quantization (02:33:46) Hugging face Role in the world of LLM/quantization (02:36:41) Localllama Sub-redit Down (Moderator goes banana) (02:40:11) Guests Hope for the Future of LLMs and AI in General Check out quantization Blog : https://cloudthrill.ca/llm-quantizati...#AI #LLM #Quantization #TechBeatsLive #Locallama #VLLM #Ollama
    Show More Show Less
    2 hrs and 51 mins
  • Ep06: "GitHub Security horror stories " (with Steve Giguere)

    Ep06: "GitHub Security horror stories " (with Steve Giguere)
    Jun 10 2025
    👨🏽‍🚀 Welcome to Episode 06 of "Tech Beats unplugged" This time, we’re diving headfirst into 𝐭𝐡𝐞 𝐜𝐫𝐚𝐳𝐢𝐞𝐬𝐭 𝐆𝐢𝐭𝐇𝐮𝐛 𝐬𝐞𝐜𝐮𝐫𝐢𝐭𝐲 𝐬𝐭𝐨𝐫𝐢𝐞𝐬, and who better to join us than Steve Giguere, an industry veteran and security expert who’s seen it all.From supply chain security mayhem to GitHub Actions gone wrong, we uncover real-world security blunders, attack vectors, and best practices to keep your repos and workflows safe.🌟 We’re so excited to share our latest tech Beats show with you🧡! Please share away 🤗We hope you'll enjoy it!!!Topics discussed: (00:00) Introduction(03:53) Software Supply Chain Security acronyms (SAST, DAST, IAST, etc.)(09:15) “A workflow is an application within your application” - What does that mean?!(12:16) Public vs. Private Repos - Are private orgs still at risk?(18:27) Self-hosted runners: Safe or security nightmare?(21:16) GitHub Environment Variables - How critical are they?(22:55) Secrets, masks, and how secure they really are (28:05) Artifact vs. Caching: Which is safer?(31:27) Craziest GitHub security screw-ups Steve has ever seen 🔥(36:42) Common attack vectors in GitHub Actions(44:19) Best security practices for GitHub Actions - Low-hanging fruit fixes 🍏(50:22) Are public actions safe? Can they be scanned?(53:52) xz backdoor fiasco - Lessons from the latest supply chain attack(59:00) NVD’s slowdown - What’s at stake?Show NotesCI/CD Goat (Deliberately vulnerable CI/CD environment): GitHubGitHub cache poisoning: Cacheract Attack | ScribeSecurityYour GitHub Secrets in Plain Text: CloudThrillGhat tool (Updating dependencies in GitHub Actions): GitHubOpenSSF Scorecard: WebsiteThe GitHub Worm (Asi Greenholts): Palo Alto BlogOWASP Top 10 CI/CD Risks: OWASPHeartbleed OpenSSL Exploit: Wikipedia🎙About Steve Giguere:⁠⁠⁠⁠Website: stevegiguere.comLinkedIn: Steve GiguereBook: Cloud Native Application Protection Platforms – O'ReillyPersonal Blog: CodifyreTalk Lessons Learned from OSS and GitOps Journey: YouTubeOWASP Lisbon Talk: YouTubeStayWiredIn YouTube Show: StayWiredInDevSecOps Podcast: Spotify
    Show More Show Less
    1 hr and 6 mins
  • Ep05: "Deploy Local LLMs 𝐢𝐧 the Cloud (𝟏𝟎𝟎% 𝐃𝐚𝐭𝐚 𝐏𝐫𝐢𝐯𝐚𝐜𝐲)"

    Ep05: "Deploy Local LLMs 𝐢𝐧 the Cloud (𝟏𝟎𝟎% 𝐃𝐚𝐭𝐚 𝐏𝐫𝐢𝐯𝐚𝐜𝐲)"
    Sep 24 2024

    👨🏽‍🚀 Welcome to Episode 05 of "Tech Beats unplugged"

    This time, we tried something completely crazy – we're letting the AI hosts take over! That's right 😎. We're flipping the script and giving the AI the mic to guide us through the fascinating world of local LLMs. but that's not all as this episode is actually inspired by my recent talk at Oracle Cloud World in Vegas. The topic? You guessed it: Local LLMs in the cloud.

    🌟 We’re so excited to share our latest tech Beats show with you🧡!

    We hope you'll enjoy it!!!

    Topics discussed:

    1. (00:00) Introduction
    2. (01:00) Why OpenAI Might Not Be Your BFF?
    3. (02:40) Local/Open LLMs to the Rescue!
    4. (03:38) What's Quantization!
    5. (04:30) Where to find these Open LLMs?
    6. (05:02) Inference Engines (Ollama)!
    7. (05:50) What's a modelfile!
    8. (06:40) What about deploying local AI to the cloud?(OKE/managed kubernetes)
    9. (07:30) From zero to cloud deployment Hero
    10. (08:28) What's Next (LLM ethic benchmark)
    11. (09:55) Outro.

    Show Notes

    • My local LLM GitRepo: Ollama_lab
    • Helm leaderboard for model safety: Sandford Helm model leaderboard
    • My talks in Oracle cloud world 2024: OCW2024LLM
    Show More Show Less
    11 mins

What listeners say about Tech Beats Unplugged

Average Customer Ratings

Reviews - Please select the tabs below to change the source of reviews.

Audible.com.au reviews

Amazon Reviews
No Reviews are Available
In the spirit of reconciliation, Audible acknowledges the Traditional Custodians of country throughout Australia and their connections to land, sea and community. We pay our respect to their elders past and present and extend that respect to all Aboriginal and Torres Strait Islander peoples today.