Sage
generate_launch_config
$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.
Remote computesage/stackbench
Remote (network-hosted)
Other tools also called generate_launch_config?
See providers with this name
Input Schema
{
"type": "object",
"properties": {
"model": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"runtime": {
"enum": [
"vllm",
"llama.cpp"
],
"type": "string"
},
"objective": {
"enum": [
"balanced",
"maximize_decode",
"maximize_prefill",
"minimize_vram",
"minimize_power",
"minimize_capex",
"minimize_tco",
"maximize_decode_per_dollar",
"maximize_prefill_per_dollar"
],
"type": "string",
"default": "balanced"
},
"batch_size": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"concurrency": {
"type": "integer",
"default": 1,
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"ubatch_size": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"quantization": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"prompt_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"engine_version": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"evidence_policy": {
"enum": [
"verified_only",
"include_public",
"all"
],
"type": "string",
"default": "include_public"
},
"flash_attention": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
]
},
"hardware_system": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"constraint_policy": {
"enum": [
"point_estimate",
"conservative"
],
"type": "string",
"default": "point_estimate"
},
"maximum_vram_bytes": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"maximum_power_watts": {
"type": "number",
"exclusiveMinimum": 0
},
"candidate_kv_formats": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 20
},
{
"type": "null"
}
]
},
"decode_context_depth": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0
},
"minimum_decode_tok_s": {
"type": "number",
"exclusiveMinimum": 0
},
"minimum_prefill_tok_s": {
"type": "number",
"exclusiveMinimum": 0
}
}
}