{"openapi":"3.1.0","info":{"title":"RYZEN-LLM Distributed API","description":"Distributed LLM inference across multiple GPUs","version":"3.0.0"},"paths":{"/health":{"get":{"summary":"Health Check","description":"Health check endpoint.","operationId":"health_check_health_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}}}}},"/metrics":{"get":{"summary":"Get Metrics","description":"Get system metrics.","operationId":"get_metrics_metrics_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}}}}},"/v1/chat/completions":{"post":{"summary":"Chat Completions","description":"Chat completions endpoint with distributed routing.","operationId":"chat_completions_v1_chat_completions_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}}},"components":{"schemas":{"ChatCompletionChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/Message"},"finish_reason":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Finish Reason"}},"type":"object","required":["index","message"],"title":"ChatCompletionChoice","description":"Single completion choice."},"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","description":"Model identifier"},"messages":{"items":{"$ref":"#/components/schemas/Message"},"type":"array","title":"Messages","description":"Conversation messages"},"temperature":{"type":"number","maximum":2.0,"minimum":0.0,"title":"Temperature","description":"Sampling temperature","default":0.7},"max_tokens":{"anyOf":[{"type":"integer","maximum":4096.0,"minimum":1.0},{"type":"null"}],"title":"Max Tokens","description":"Maximum tokens to generate","default":256},"stream":{"type":"boolean","title":"Stream","description":"Enable streaming response","default":false},"gpu_preference":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Gpu Preference","description":"Preferred GPU ID (optional)"}},"type":"object","required":["model","messages"],"title":"ChatCompletionRequest","description":"Chat completion request for distributed inference."},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionChoice"},"type":"array","title":"Choices"},"usage":{"additionalProperties":{"type":"integer"},"type":"object","title":"Usage"}},"type":"object","required":["id","created","model","choices","usage"],"title":"ChatCompletionResponse","description":"Chat completion response."},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"Message":{"properties":{"role":{"type":"string","title":"Role","description":"Role: system, user, or assistant"},"content":{"type":"string","title":"Content","description":"Message content"}},"type":"object","required":["role","content"],"title":"Message","description":"Chat message."},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}}