Skip to main content

Module application

Module application 

Source

Modules§

events

Structs§

LifecycleOptions
PlanOptions
QuantPlan
SpeculationPlan
How a launch will speculate, decided before any side effect.

Functions§

auto_backend_order
Backends compatible with the model, in auto-selection order; MLX leads only on Apple Silicon. Attach-only LM Studio is never auto-selected (spec Q1).
check_attach_override
Attach-intent commands follow the active backend; a conflicting override must fail, not be ignored.
check_backend
drafter_reserve
hardware with the drafter’s catalog memory and download ceiling set aside.
forget_attached_with_config
down --forget: clears a stale attached pointer without probing or signalling any process.
installed_inventory
kv_slot_directory
Where llama.cpp servers rigspark starts keep saved KV slots: kv-slots/ beside the runtime state file, created private to this user.
kv_slot_directory_for
The KV slot directory a server of backend starts with: llama.cpp only.
kv_slot_with_config
Saves, restores or erases a KV slot on the llama.cpp server this config’s state records. Lets a caller free a slot during a long pause (a tool call) and bring it back after.
plan_quantization
Picks the quantization to pull and enforces fit, bypass and disk preflight before any side effect.
plan_speculation
Resolves auto (and the llama.cpp default when no flag was given) to a concrete mode.
preferred_backend
Flag, then non-blank RIGSPARK_BACKEND, then the user config default.
run_native
run_native_observed
run_native_with_config
run_native_with_config_observed
slot_sizing_model
The model as sized for concurrent slots: Ollama allocates a full context per slot, llama.cpp shares one unified KV pool.
validate_backend_platform