AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)
Donato Capitella
AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)
29:25
Strix Halo & R9700 AI PRO Updates: Qwen 3.6 and Gemma 4 Support, ROCm 7.2.2 and Two New Series
Donato Capitella
Strix Halo & R9700 AI PRO Updates: Qwen 3.6 and Gemma 4 Support, ROCm 7.2.2 and Two New Series
15:01
Fast Finetuning of Gemma-3, Qwen-3 and GPT-OSS on Strix Halo using Unsloth and Multi-Node Setups
Donato Capitella
Fast Finetuning of Gemma-3, Qwen-3 and GPT-OSS on Strix Halo using Unsloth and Multi-Node Setups
31:45
ComfyUI Strix Halo Toolbox for Image and Video Generation (LTX2, Qwen Image, WAN 2.2, Hunyuan 1.5)
Donato Capitella
ComfyUI Strix Halo Toolbox for Image and Video Generation (LTX2, Qwen Image, WAN 2.2, Hunyuan 1.5)
18:12
Low-Latency Strix Halo Cluster with RDMA (RoCE/Intel E810) and vLLM, Framework Desktop Boards
Donato Capitella
Low-Latency Strix Halo Cluster with RDMA (RoCE/Intel E810) and vLLM, Framework Desktop Boards
16:18
Kimi-K2(1T)/GLM 4.7(355B) on a 4-Node Strix Halo Cluster - 512GB of Unified Memory
Donato Capitella
Kimi-K2(1T)/GLM 4.7(355B) on a 4-Node Strix Halo Cluster - 512GB of Unified Memory
9:36
ROCm+Linux Support on Strix Halo: It's finally stable in 2026!
Donato Capitella
ROCm+Linux Support on Strix Halo: It's finally stable in 2026!
12:20
Video and Image Generation on AMD R9700 AI PRO (Qwen Image, Wan 2.2, Hunyuan 1.5)
Donato Capitella
Video and Image Generation on AMD R9700 AI PRO (Qwen Image, Wan 2.2, Hunyuan 1.5)
41:36
Running vLLM on Strix Halo (AMD Ryzen AI MAX) + ROCm Performance Updates
Donato Capitella
Running vLLM on Strix Halo (AMD Ryzen AI MAX) + ROCm Performance Updates
18:06
vLLM on Dual AMD Radeon 9700 AI PRO: Tutorials, Benchmarks (vs RTX 5090/5000/4090/3090/A100)
Donato Capitella
vLLM on Dual AMD Radeon 9700 AI PRO: Tutorials, Benchmarks (vs RTX 5090/5000/4090/3090/A100)
23:39
Dual AMD Radeon 9700 AI PRO: Building a 64GB LLM/AI Server with Llama.cpp
Donato Capitella
Dual AMD Radeon 9700 AI PRO: Building a 64GB LLM/AI Server with Llama.cpp
50:30
Building a Two-Node AMD Strix Halo Cluster for LLMs with llama.cpp RPC (MiniMax-M2 & GLM 4.6)
Donato Capitella
Building a Two-Node AMD Strix Halo Cluster for LLMs with llama.cpp RPC (MiniMax-M2 & GLM 4.6)
26:53
Finetuning LLMs on Strix Halo – Full, LoRA, and QLoRA on Gemma-3, Qwen-3, and GPT-OSS-20B
Donato Capitella
Finetuning LLMs on Strix Halo – Full, LoRA, and QLoRA on Gemma-3, Qwen-3, and GPT-OSS-20B
55:05
VibeVoice (Speech Generation/Voice Cloning) on Framework Desktop with Strix Halo (AMD AI Ryzen MAX+)
Donato Capitella
VibeVoice (Speech Generation/Voice Cloning) on Framework Desktop with Strix Halo (AMD AI Ryzen MAX+)
13:17
Run Qwen Image and WAN 2.2 on Framework Desktop with Strix Halo (AMD AI Ryzen MAX+ 395) - Full Guide
Donato Capitella
Run Qwen Image and WAN 2.2 on Framework Desktop with Strix Halo (AMD AI Ryzen MAX+ 395) - Full Guide
24:44
GLM 4.5-Air-106B and Qwen3-235B on AMD "Strix Halo" AI Ryzen MAX+ 395 (HP Z2 G1a Mini Workstation)
Donato Capitella
GLM 4.5-Air-106B and Qwen3-235B on AMD "Strix Halo" AI Ryzen MAX+ 395 (HP Z2 G1a Mini Workstation)
26:40
Zero-Click M365 Copilot Exploit 'EchoLeak' - Deep Dive
Donato Capitella
Zero-Click M365 Copilot Exploit 'EchoLeak' - Deep Dive
38:17
Spikee #4 - Bypassing LLM Guardrails (Anti-spotlighting, Best of N attacks)
Donato Capitella
Spikee #4 - Bypassing LLM Guardrails (Anti-spotlighting, Best of N attacks)
47:01
Spikee #3 - Prompt Injection Testing of a GenAI Feature in an LLM Application
Donato Capitella
Spikee #3 - Prompt Injection Testing of a GenAI Feature in an LLM Application
23:11
Spikee #2 - Hands-on Prompt Injection Testing with Custom Dataset
Donato Capitella
Spikee #2 - Hands-on Prompt Injection Testing with Custom Dataset
34:05
Spikee #1 - LLM Benchmarking/Testing Tool for Prompt Injection
Donato Capitella
Spikee #1 - LLM Benchmarking/Testing Tool for Prompt Injection
29:27
Hacking and Securing LLM Applications - Should you let ChatGPT Control Your Browser [DeepSec 2024]
Donato Capitella
Hacking and Securing LLM Applications - Should you let ChatGPT Control Your Browser [DeepSec 2024]
39:56
Multi-Chain Prompt Injection and Jailbreaking of LLM Applications
Donato Capitella
Multi-Chain Prompt Injection and Jailbreaking of LLM Applications
47:10
Microsoft 365 Copilot Hack Breakdown [Black Hat 2024]
Donato Capitella
Microsoft 365 Copilot Hack Breakdown [Black Hat 2024]
21:24
The ADAM Optimizer, Momentum and RMSProp
Donato Capitella
The ADAM Optimizer, Momentum and RMSProp
2:49
Update Strategies: Full Batch / Incremental, Stochastic Gradient Descent with Mini-Batches
Donato Capitella
Update Strategies: Full Batch / Incremental, Stochastic Gradient Descent with Mini-Batches
3:48
The Training Loop of a Neural Network
Donato Capitella
The Training Loop of a Neural Network
2:23
Gradient Descent to Train a Neural Network
Donato Capitella
Gradient Descent to Train a Neural Network
2:37
Dataset Split (Train, Test, Validation)
Donato Capitella
Dataset Split (Train, Test, Validation)
1:42
Data Normalization
Donato Capitella
Data Normalization
1:33
What's the Loss Function?
Donato Capitella
What's the Loss Function?
2:22
Preparing Datasets for Training Neural Networks
Donato Capitella
Preparing Datasets for Training Neural Networks
3:07
[Google Gemini] Prompt Injection via Email for Social Engineering Attacks
Donato Capitella
[Google Gemini] Prompt Injection via Email for Social Engineering Attacks
1:10
Indirect Prompt Injection in Langchain/GPT4 Email Agent
Donato Capitella
Indirect Prompt Injection in Langchain/GPT4 Email Agent
9:37
Tensors and GPUs
Donato Capitella
Tensors and GPUs
1:33
Matrix Multiplications in Neural Networks
Donato Capitella
Matrix Multiplications in Neural Networks
1:27
Prompt Injection / JailBreaking a Banking LLM Agent (GPT-4, Langchain)
Donato Capitella
Prompt Injection / JailBreaking a Banking LLM Agent (GPT-4, Langchain)
12:09
Outputs of Neural Networks for Classification and Regression Tasks
Donato Capitella
Outputs of Neural Networks for Classification and Regression Tasks
2:33
Modelling inputs to a Neural Network
Donato Capitella
Modelling inputs to a Neural Network
2:08
Multi-Layer Perceptrons
Donato Capitella
Multi-Layer Perceptrons
2:49
Perceptrons and Artificial Neurons
Donato Capitella
Perceptrons and Artificial Neurons
2:48
[Webinar] Building LLM applications in a secure way (WithSecure™)
Donato Capitella
[Webinar] Building LLM applications in a secure way (WithSecure™)
56:52
Prompt Injection in LLM Browser Agents
Donato Capitella
Prompt Injection in LLM Browser Agents
12:50
Prompt Injection in LLM Agents (ReAct, Langchain)
Donato Capitella
Prompt Injection in LLM Agents (ReAct, Langchain)
19:28
Donato Capitella Live Stream
Donato Capitella
Donato Capitella Live Stream