42 lines
1.1 KiB
JSON
42 lines
1.1 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"catalogue_version": "2026.07.1",
|
|
"recipes": [
|
|
{
|
|
"id": "baseline",
|
|
"version": "1",
|
|
"backend_id": "torch-transformers",
|
|
"description": "Backend defaults with no execution overrides.",
|
|
"params": {}
|
|
},
|
|
{
|
|
"id": "eager-attention",
|
|
"version": "1",
|
|
"backend_id": "torch-transformers",
|
|
"description": "Force the reference attention path instead of the backend's autoselected one.",
|
|
"params": {
|
|
"attn_implementation": "eager"
|
|
}
|
|
},
|
|
{
|
|
"id": "stateless",
|
|
"version": "1",
|
|
"backend_id": "torch-transformers",
|
|
"description": "Disable the incremental state cache; every step re-runs the full prefill.",
|
|
"params": {
|
|
"use_cache": false
|
|
}
|
|
},
|
|
{
|
|
"id": "llama-cpp-native",
|
|
"version": "1",
|
|
"backend_id": "llama.cpp",
|
|
"description": "Project-owned native GGUF worker behind the Meshnet control plane.",
|
|
"params": {
|
|
"worker_transport": "grpc",
|
|
"use_cache": true
|
|
}
|
|
}
|
|
]
|
|
}
|