beye.blog logo
LLM

3 posts tagged with LLM

Building a Two-Node LLM Inference Cluster on NVIDIA GX10 (GB10)
AI

Building a Two-Node LLM Inference Cluster on NVIDIA GX10 (GB10)

Two GX10 boxes, a 230B MoE coding model, and one flag I should never have set. How 25 tok/s became 40.4, and why it stops there.

• 17 min read
Share:
EVPN in a Box Part 3: CI/CD, an LLM That Talks to Your Lab, and the Memory Wall
Cisco Technologies

EVPN in a Box Part 3: CI/CD, an LLM That Talks to Your Lab, and the Memory Wall

The final stretch: adding a GitLab CI/CD pipeline, wiring an LLM into the lab through MCP, and discovering that the lite NX-OS image can't actually run BGP EVPN.

• 12 min read
Share:
Building an AI-Powered Webhook Platform for Splunk and ServiceNow
Automation

Building an AI-Powered Webhook Platform for Splunk and ServiceNow

How a Cisco Live lab scenario turned into a full microservices platform for managing Splunk webhooks with LLM-enhanced ServiceNow ticket creation.

• 8 min read
Share: