Red Hat Emerging Technologies next.redhat.com

Zero trust for AI agents: why delegation beats impersonation

next.redhat.com·1d

Who’s really calling? Securing agent-to-agent communication

next.redhat.com·1w

Code execution with MCP: How sandboxed Python replaces tool schema bloat in AI agents

next.redhat.com·4w

PyTorch Call Stack Deep Dive: Tracing Tensor Operations from Python to C++ Kernels

next.redhat.com·8w

Eliminating the ‘Rego tax’: How AI orchestrators automate Kubernetes compliance

next.redhat.com·9w

Zero trust AI agents on Kubernetes: What I learned deploying multi-agent systems on Kagenti

next.redhat.com·11w

Zero Trust for autonomous agentic AI systems: Building more secure foundations

next.redhat.com·12w

From hand-tuned to generated: A reproducible Triton GPU kernel benchmark across different vendors

next.redhat.com·14w

Protecting Triton kernel deployments with cryptographic signatures

next.redhat.com·15w

Skip the JITters: Fast, trusted model kernels with OCI caching

next.redhat.com·16w

Architecting Cloud-Native Ambient Agents: Patterns for Scale and Control

next.redhat.com·17w

Simplifying Edge AI Builds with Verified GitHub Actions Patterns

next.redhat.com·23w

A Practical Approach to Smart Tool Retrieval for Enterprise AI Agents

next.redhat.com·24w

Tool RAG: The Next Breakthrough in Scalable AI Agents

next.redhat.com·25w

Triton Kernel Profiling with NVIDIA Nsight Tools

next.redhat.com·26w

Intelligent inference request routing for large language models

next.redhat.com·27w

Enhancing AI inference security with confidential computing: A path to private data inference with proprietary LLMs

next.redhat.com·30w

A developer’s guide to PyTorch, containers, and NVIDIA – Solving the puzzle

next.redhat.com·38w

Understanding Triton Cache: Optimizing GPU Kernel Compilation

next.redhat.com·53w

Model authenticity and transparency with Sigstore

next.redhat.com·58w

Log in to enable infinite scrolling