Auteur • 198 livres
ONNX Runtime GenAI : Portable Inference Across CPU, GPU, and Edge
Trex Team
AWQ Quantization : Shipping 4‑Bit LLMs Without Quality Face‑Plants
GPTQ in Production : Quantize, Validate, and Serve Efficient LLMs
OpenVINO for GenAI : CPU‑First Acceleration and Edge Deployment Strategies
OWASP for LLM Apps : A Practical Security Checklist for GenAI Product Teams
Speculative Decoding Systems : Faster Generation with Draft Models and Safety Checks
DeepSpeed Inference : Tensor Parallelism and Memory Efficiency for Large Models
FlashAttention : Speeding Up Transformers with Modern Attention Kernels
NIST AI RMF in Engineering : Turning Risk Management into Shipping Controls
ISO/IEC 42001 for AI : Building an AI Management System Engineers Can Operate
Threat Modeling GenAI Apps : Assets, Attack Paths, and Controls That Work
Stopping LLM Data Exfiltration : DLP Patterns for Prompts, Logs, and Retrieval
Engineering for the EU AI Act : Technical Controls for GPAI and High‑Risk Systems
Prompt Injection Defense : Hardening RAG, Tools, and System Prompts
Agent Communication Protocol (ACP) : Designing Secure Agent‑to‑Agent APIs and Workflows
Practical Federated Learning Systems : Privacy‑Preserving Training Across Devices and Orgs
Differential Privacy for ML Engineers : Practical Budgets, Noise, and Tradeoffs
Helmfile Patterns : Managing Hundreds of Helm Releases Predictably
Red‑Teaming LLM Applications : Building Test Suites for Jailbreaks and Abuse
AI Incident Response : Playbooks for Prompt Leaks, Tool Abuse, and Model Failures
Membership Inference & Privacy Leakage : Measuring and Reducing Data Exposure
Poisoning Attacks on ML Pipelines : Detection, Response, and Resilient Training
Model Extraction and Theft : How Deployed Models Get Stolen—and How to Stop It
Policy‑as‑Code for GenAI : Enforcing Safety and Compliance in CI/CD
Agent2Agent Protocol (A2A) : Building Interoperable Multi‑Agent Systems Across Vendors
FIDO Device Onboard : Zero‑Touch Provisioning for Secure IoT Fleets
Passkeys Everywhere : Shipping WebAuthn Authentication Without UX Pain
Modern OAuth Security : OAuth 2.1, PAR, RAR, and DPoP for API Engineers
Secure RAG Authorization : Row‑Level Security, ACLs, and Per‑User Retrieval
Model Governance at Scale : Registries, Approvals, and Lifecycle Controls
C2PA Content Credentials : Engineering Provenance for AI‑Generated Media
Audit‑Ready GenAI : Logging, Evidence, and Explainability Without Killing Velocity
Safety Evaluation Engineering : From Red Flags to Measurable, Repeatable Safety Gates
SCIM 2.0 in Practice : Automated User Provisioning and Identity Lifecycle for SaaS
MLS for Engineers : Secure Group Messaging That Actually Scales
Verifiable Credentials & DIDs : Wallets, OIDC Flows, SD‑JWT, and Secure Messaging
36 de 198 titres
