41554 blogs · [
{
"id": "01a08796-f393-711f-9fb4-960a98e1dea2",
"title": "What Is LLM-as-a-Judge, Really? A Field Guide to the State of the Art in 2026",
"url": "https://kraghavan.ca/llm-infrastructure/evaluation/2026/07/25/llm-as-a-judge-field-guide.html",
"published_at": "2026-07-25T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf37831a9",
"title": "Software Layers Before Inference At Scale",
"url": "https://kraghavan.ca/2026/04/30/software-layers-before-inference-at-scale.html",
"published_at": "2026-04-30T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf438de86",
"title": "I Built a Five-Agent SRE War Room and Grafana Watched Every Token",
"url": "https://kraghavan.ca/llm-infrastructure/observability/grafana/2026/04/25/sre-war-room-grafana-observbility.html",
"published_at": "2026-04-25T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf4e9ce73",
"title": "P/D Disaggregation on a Single GPU — What the Architecture Actually Requires",
"url": "https://kraghavan.ca/llm-infrastructure/inference/2026/04/21/llm-d-pd-disaggregation.html",
"published_at": "2026-04-21T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf5ab0156",
"title": "llm-d in Action — EPP Prefix Cache Routing and What It Actually Means",
"url": "https://kraghavan.ca/llm-infrastructure/inference/2026/04/19/llm-d-epp-prefix-cache-results.html",
"published_at": "2026-04-19T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf60900bd",
"title": "Deploying llm-d on a Cloud GPU — The 10 Things Nobody Tells You",
"url": "https://kraghavan.ca/llm-infrastructure/inference/2026/04/17/vllm-llm-d-nvidia-gh200-experiment.html",
"published_at": "2026-04-17T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf6208720",
"title": "Treating the M4 Mac Mini Like a Production Inference Server (It Tried)",
"url": "https://kraghavan.ca/llm-infrastructure/inference/2026/04/16/vllm-ollama-apple-silicon-experiment2.html",
"published_at": "2026-04-16T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf69f922a",
"title": "What Is LLM Inference, Really? A Deep Technical Walkthrough",
"url": "https://kraghavan.ca/llm-infrastructure/inference/2026/04/14/re-introduction-to-inference.html",
"published_at": "2026-04-14T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf782b6f6",
"title": "Schema Travels Architecture",
"url": "https://kraghavan.ca/2026/04/06/schema-travels-architecture.html",
"published_at": "2026-04-06T00:00:00+00:00"
},
{
"id": "01a08796-f394-72be-bcba-c4ccf86f649b",
"title": "Building a Privacy-Aware LLM Gateway: Benchmarking Results",
"url": "https://kraghavan.ca/llm/infrastructure/benchmarks/2026/03/21/inference-sentinel-benchmarks2.html",
"published_at": "2026-03-21T00:00:00+00:00"
}
] posts Claim your blog