operationsJun 25, 2026· 6m
How to warm an LLM cache during a model migration
How to warm an LLM cache during a model migration. A practical, Crowkis-grounded take, no hype, just what actually moves cost, latency, and safety.
← the Roost
Topic · 16 posts
Operations
Running Crowkis in production: deployment, hardening, observability, budgets, and day-2 work.
operationsJun 18, 2026· 5m
Per-tenant rate limits (CKEYLIMIT): how it works and when to use it
Per-tenant rate limits (CKEYLIMIT), caps requests and tokens per minute per tenant, enforced at the cache before the spend happens. Here's how Crowkis does it and why it matters for cost and safety.
operationsJun 12, 2026· 5m
Semantic dedup (CDEDUP): how it works and when to use it
Semantic dedup (CDEDUP), folds near-duplicate answers into clusters and reports the memory reclaimed, best run as scheduled off-peak maintenance. Here's how Crowkis does it and why it matters for cost and safety.
operationsJun 9, 2026· 5m
Observability dashboard + Prometheus: how it works and when to use it
Observability dashboard + Prometheus, shows hit rate, saved spend, safety blocks, and memory pressure live, and exposes Prometheus /metrics, all in the box. Here's how Crowkis does it and why it matters for cost and safety.
operationsJun 8, 2026· 3m
The five-minute deploy, timed honestly
Pull, run, first hit in the dashboard, with no config file, no signup, and no environment variables you're required to set. We timed it. It holds.
operationsJun 5, 2026· 3m
Upgrades as non-events: the binary-swap contract
docker pull, restart, done, no schema migrations, no export/import, no upgrade runbook. The on-disk format is a stability promise, not an implementation detail.
operationsJun 2, 2026· 5m
Model migration without a cold cache: how it works and when to use it
Model migration without a cold cache, canary and migration workflows carry cache value across a model upgrade, so a new model doesn't cold-start your hit rate. Here's how Crowkis does it and why it matters for cost and safety.
operationsJun 2, 2026· 3m
Three windows into one cache: dashboard, Prometheus, logs
The built-in dashboard for humans, /metrics for your Grafana, one JSON line per event for your pipeline, same truth, three consumers, zero adapters.
operationsMay 30, 2026· 3m
Crowkis on Kubernetes: a well-behaved citizen
One container, a PVC, real health probes, hard memory bounds, graceful shutdown. Everything your cluster expects from a tenant that's read the manual.
operationsMay 26, 2026· 3m
Running a model canary: the operator's walkthrough
Slice the traffic, compare against cached baselines, promote or retreat, model upgrades as a controlled experiment with the cache as your measuring instrument.
operationsMay 23, 2026· 3m
Fallback routing: surviving your provider's bad day
Providers have incidents; your product doesn't have to. Health-aware backend routing plus a warm cache turns upstream outages into degraded modes users barely notice.
operationsMay 20, 2026· 3m
Memory governance: a cache that respects its container
CROWKIS_MEMORY_LIMIT means what it says, no GC mood swings, no mystery RSS, eviction that engages before the kernel has opinions.
operationsMay 17, 2026· 3m
A tour of the dashboard: six panels, zero mysteries
Live verdicts, hit-type economics, top misses, safety blocks, tenant accounting, system pressure, what each panel answers and who keeps it open.
operationsMay 14, 2026· 3m
The world's shortest cache runbook
Fail-open design means most 'incidents' are the absence of savings, not the presence of errors. Here's the whole decision tree, which fits on an index card.
operationsMay 11, 2026· 3m
Boring on purpose: the operational philosophy
Exciting infrastructure is a contradiction in terms. Every Crowkis design decision optimizes for the same review: 'it just runs.'
operationsFeb 17, 2026· 6m
LLM observability: what to actually measure
LLM observability: what to actually measure. A practical, Crowkis-grounded take, no hype, just what actually moves cost, latency, and safety.