Skip to main content

EXTENSIONS

Built by operatives — models, drivers, vaults, and reports, the parts that plug into Swamp.

Filter by what you need and pull what fits.

Selection
4 results
label:inference

Cost Projection

@webframp/cost-projection · v2026.08.21.2

GPU inference cost projection across cloud, rental, and capex scenarios.

upd Aug 223 pullsA100/100

Cloudflare/workers Ai

@webframp/cloudflare/workers-ai · v2026.08.21.2

Cloudflare Workers AI — model inference, fine-tuning, LoRA adapters

upd Aug 220 pullsA100/100

Scaleway Inference

@sntxrr/scaleway-inference · v2026.07.19.1

Manage a Scaleway Managed Inference deployment — sync state, create, update, and delete dedicated model serving deployments, and discover deployments in a region, via the Managed Inference API with X-Auth-Token auth.

upd Jul 190 pullsA100/100

Llm Catalog

@stateless/llm-catalog · v2026.06.23.1

A sourced, versioned knowledge base of LLM-ops knowledge — NOT a control plane for running models, but the structured, CEL-queryable record that running extensions read to decide which model to run where, with what settings, at what cost. Six subject kinds (model, runtime, provider, hardware, technique, endpoint), all the same uniform `entry` shape (open kind + open facets, like @stateless/inventory); a model's run-options embed on the model in runsOn[] keyed by endpoint, and capacity/plan answer "what to run where" over them. The twist: it records external, decaying knowledge, so every volatile assertion carries a provenance envelope (asOf, source, versionPins, supersededBy) — "best vLLM version" is derived as the latest un-superseded claim, never a bare rotting field. Declarative: `apply` materialises one `entry` resource per id (re-run = versioned trend); `prune` soft-retires undeclared entries.

upd Jun 230 pullsA100/100