472a5a3473
Thin HTTP client for the resident oMLX server on :8020 (launchd party.monster.deepseek-v4, repo monster/deepseek_v4_flash_0731_mrp_mlx). gpu lane so the queue serializes LLM calls against mesh/image gen on this node. Kickstarts the service if down. Primary-only — ~150GB wired warm. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
20 lines
1.0 KiB
JSON
20 lines
1.0 KiB
JSON
{
|
|
"id": "llm_v4",
|
|
"name": "LLM (DeepSeek-V4-Flash 304B, local)",
|
|
"category": "text",
|
|
"description": "Prompt → text via DeepSeek-V4-Flash-0731 (304B MoE, 13B active) served by oMLX on :8020. ~45 tok/s warm with DSpark speculative decode, 1M context capable. The heavyweight for hard reasoning/code; for quick/cheap calls use the m4pro Ollama endpoint, for mid-tier use llm_local. Primary-node only — the server holds ~150GB wired. gpu lane so the queue serializes it against mesh/image gen on this box.",
|
|
"accepts": [],
|
|
"produces": ["text"],
|
|
"resources": "gpu",
|
|
"entry": "run.py",
|
|
"params_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"prompt": {"type": "string", "default": "", "description": "The user prompt"},
|
|
"system": {"type": "string", "default": "", "description": "Optional system prompt"},
|
|
"max_tokens": {"type": "integer", "default": 1024, "minimum": 16, "maximum": 32768},
|
|
"temperature": {"type": "number", "default": 0.7, "minimum": 0, "maximum": 2}
|
|
}
|
|
}
|
|
}
|