Skip to main content

EXTENSIONS

Selection
5 results
label:inference

Halogen Flash Server

@randomfrequency/halogen-flash-server · v2026.11.14.1

Install and manage Peonist Halogen Flash Server containers on AMD Strix Halo systems.

upd Nov 142 pullsA100/100

Cost Projection

@webframp/cost-projection · v2026.11.03.1

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

upd Nov 453 pullsA100/100

Cloudflare/workers Ai

@webframp/cloudflare/workers-ai · v2026.11.03.1

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

upd Nov 445 pullsA100/100

Scaleway Inference

@sntxrr/scaleway-inference · v2026.10.14.1

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 Oct 1429 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a provenance envelope (asOf, source, versionPins, supersededBy) — "best vLLM version" is derived as the latest un-superseded claim, never a bare rotting field.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 2330 pullsA93/100