// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright contributors to the vLLM project

syntax = "proto3";
package vllm;

service Control {
  rpc GetServerInfo (GetServerInfoRequest) returns (ServerInfo) {}
  rpc GetModelInfo (GetModelInfoRequest) returns (ModelInfo) {}
  rpc Abort (AbortRequest) returns (AbortResponse) {}
  rpc GetKvEventSources (GetKvEventSourcesRequest) returns (GetKvEventSourcesResponse) {}
}

message GetServerInfoRequest {}

message ServerInfo {
  string engine_version = 1;
  string api_version = 2;
  string instance_id = 3;
  ParallelismInfo parallelism = 4;
  uint32 max_model_len = 5;
  uint32 kv_block_size = 6;
  uint64 total_kv_blocks = 7;
  uint64 max_running_requests = 8;
  uint64 max_batched_tokens = 9;
}

message ParallelismInfo {
  uint32 tensor_parallel_size = 1;
  uint32 pipeline_parallel_size = 2;
  uint32 data_parallel_size = 3;
  uint32 data_parallel_rank = 4;
  uint32 decode_context_parallel_size = 5;
}

message GetModelInfoRequest {}

message ModelInfo {
  string model_id = 1;
  string served_model_name = 2;
  repeated string served_model_aliases = 3;

  bool supports_text_input = 20;
  bool supports_token_ids_input = 21;
  bool supports_multimodal = 23;
  string reasoning_parser = 24;
  string tool_call_parser = 25;
}

message AbortRequest {
  repeated string request_ids = 1;
}

message AbortResponse {}

// ======================================================================================
// KV discovery
// ======================================================================================

message GetKvEventSourcesRequest {}
message GetKvEventSourcesResponse { repeated KvEventSource sources = 1; }

message KvEventSource {
  string transport = 1;
  string endpoint = 2;
  string topic = 3;
  string replay_endpoint = 4;
  optional uint32 data_parallel_rank = 5;
  string encoding = 6;
  uint32 schema_version = 7;
  uint32 buffer_steps = 8;
  uint32 hwm = 9;
  uint32 max_queue_size = 10;
}