fidecastro
62d8e18efd
- Complete llama-server API client implementation - Support for all 8 endpoints (completion, chat, embeddings, etc.) - 100+ parameters including advanced sampling (DRY, XTC, Mirostat) - Multimodal support with image processing - Function calling and tool use capabilities - Grammar and JSON Schema constraints - LoRA adapter configuration - Comprehensive documentation and examples - Testing infrastructure included - Professional README with badges and usage examples
35 lines
968 B
JSON
35 lines
968 B
JSON
{
|
|
"name": "ComfyUI Llama.cpp Client Node",
|
|
"version": "1.0.0",
|
|
"description": "Comprehensive ComfyUI custom node for llama-server client with complete API support",
|
|
"author": "AI Assistant",
|
|
"license": "MIT",
|
|
"comfyui_version": ">=1.0.0",
|
|
"dependencies": [
|
|
"requests>=2.25.1",
|
|
"pillow>=8.0.0"
|
|
],
|
|
"supported_endpoints": [
|
|
"completion",
|
|
"chat_completions",
|
|
"embeddings",
|
|
"tokenize",
|
|
"detokenize",
|
|
"apply_template",
|
|
"infill",
|
|
"reranking"
|
|
],
|
|
"features": [
|
|
"Advanced sampling (DRY, XTC, Mirostat, Dynamic Temperature)",
|
|
"Grammar and JSON Schema constraints",
|
|
"Multimodal image support",
|
|
"Function calling and tool use",
|
|
"LoRA adapter configuration",
|
|
"KV cache management",
|
|
"Streaming support",
|
|
"Complete parameter coverage"
|
|
],
|
|
"node_count": 1,
|
|
"category": "AI/LlamaCpp"
|
|
}
|