|
| 1 | +//! ONNX Runtime serving adapter used by the serving RPC boundary. |
| 2 | +
|
| 3 | +use super::serving::{ |
| 4 | + effective_gateway_alias_from_config, non_critical_failure_response, serving_error, |
| 5 | +}; |
| 6 | +use crate::server::AppState; |
| 7 | +use pumas_library::models::{ |
| 8 | + ModelServeErrorCode, RuntimeProfileId, RuntimeProviderId, ServeModelRequest, |
| 9 | + ServeModelResponse, ServedModelLoadState, ServedModelStatus, UnserveModelRequest, |
| 10 | + UnserveModelResponse, |
| 11 | +}; |
| 12 | +use pumas_library::{ExecutableArtifactFormat, OnnxLoadOptions, OnnxLoadRequest, OnnxModelId}; |
| 13 | +use serde_json::Value; |
| 14 | +use tracing::warn; |
| 15 | + |
| 16 | +pub(super) async fn serve_onnx_model( |
| 17 | + state: &AppState, |
| 18 | + request: ServeModelRequest, |
| 19 | +) -> pumas_library::Result<Value> { |
| 20 | + let Some(onnx_path) = resolve_onnx_model_path(state, &request).await? else { |
| 21 | + return non_critical_failure_response( |
| 22 | + state, |
| 23 | + serving_error( |
| 24 | + ModelServeErrorCode::ModelNotExecutable, |
| 25 | + "model has no executable ONNX artifact", |
| 26 | + &request, |
| 27 | + ), |
| 28 | + ) |
| 29 | + .await; |
| 30 | + }; |
| 31 | + let library_root = state.api.model_library().library_root().to_path_buf(); |
| 32 | + let load_request = match OnnxLoadRequest::parse( |
| 33 | + library_root, |
| 34 | + &onnx_path, |
| 35 | + &request.model_id, |
| 36 | + OnnxLoadOptions::default(), |
| 37 | + ) { |
| 38 | + Ok(load_request) => load_request, |
| 39 | + Err(error) => { |
| 40 | + warn!("ONNX serving load request validation failed: {}", error); |
| 41 | + return non_critical_failure_response( |
| 42 | + state, |
| 43 | + serving_error( |
| 44 | + ModelServeErrorCode::InvalidRequest, |
| 45 | + "ONNX Runtime rejected the selected model load request", |
| 46 | + &request, |
| 47 | + ), |
| 48 | + ) |
| 49 | + .await; |
| 50 | + } |
| 51 | + }; |
| 52 | + |
| 53 | + let session = match state.onnx_session_manager.load(load_request).await { |
| 54 | + Ok(session) => session, |
| 55 | + Err(error) => { |
| 56 | + warn!("ONNX fake session load failed: {}", error); |
| 57 | + return non_critical_failure_response( |
| 58 | + state, |
| 59 | + serving_error( |
| 60 | + ModelServeErrorCode::ProviderLoadFailed, |
| 61 | + "ONNX Runtime could not load the selected model", |
| 62 | + &request, |
| 63 | + ), |
| 64 | + ) |
| 65 | + .await; |
| 66 | + } |
| 67 | + }; |
| 68 | + |
| 69 | + let status = ServedModelStatus { |
| 70 | + model_id: request.model_id.clone(), |
| 71 | + model_alias: Some(effective_gateway_alias_from_config(&request)), |
| 72 | + provider: RuntimeProviderId::OnnxRuntime, |
| 73 | + profile_id: request.config.profile_id.clone(), |
| 74 | + load_state: ServedModelLoadState::Loaded, |
| 75 | + device_mode: request.config.device_mode, |
| 76 | + device_id: request.config.device_id.clone(), |
| 77 | + gpu_layers: request.config.gpu_layers, |
| 78 | + tensor_split: request.config.tensor_split.clone(), |
| 79 | + context_size: Some(session.embedding_dimensions as u32), |
| 80 | + keep_loaded: request.config.keep_loaded, |
| 81 | + endpoint_url: None, |
| 82 | + memory_bytes: None, |
| 83 | + loaded_at: None, |
| 84 | + last_error: None, |
| 85 | + }; |
| 86 | + let snapshot = state.api.record_served_model(status.clone()).await?; |
| 87 | + |
| 88 | + Ok(serde_json::to_value(ServeModelResponse { |
| 89 | + success: true, |
| 90 | + error: None, |
| 91 | + loaded: true, |
| 92 | + loaded_models_unchanged: false, |
| 93 | + status: Some(status), |
| 94 | + load_error: None, |
| 95 | + snapshot: Some(snapshot), |
| 96 | + })?) |
| 97 | +} |
| 98 | + |
| 99 | +pub(super) async fn unserve_onnx_model( |
| 100 | + state: &AppState, |
| 101 | + request: UnserveModelRequest, |
| 102 | + profile_id: RuntimeProfileId, |
| 103 | + model_alias: String, |
| 104 | +) -> pumas_library::Result<Value> { |
| 105 | + let model_id = match OnnxModelId::parse(&request.model_id) { |
| 106 | + Ok(model_id) => model_id, |
| 107 | + Err(error) => { |
| 108 | + warn!("ONNX serving unload request validation failed: {}", error); |
| 109 | + return Ok(serde_json::to_value(UnserveModelResponse { |
| 110 | + success: true, |
| 111 | + error: Some("ONNX Runtime rejected the selected model unload request".to_string()), |
| 112 | + unloaded: false, |
| 113 | + snapshot: Some(state.api.get_serving_status().await?.snapshot), |
| 114 | + })?); |
| 115 | + } |
| 116 | + }; |
| 117 | + |
| 118 | + match state.onnx_session_manager.unload(&model_id).await { |
| 119 | + Ok(Some(_)) => {} |
| 120 | + Ok(None) => { |
| 121 | + return Ok(serde_json::to_value(UnserveModelResponse { |
| 122 | + success: true, |
| 123 | + error: Some("ONNX Runtime model was not loaded".to_string()), |
| 124 | + unloaded: false, |
| 125 | + snapshot: Some(state.api.get_serving_status().await?.snapshot), |
| 126 | + })?); |
| 127 | + } |
| 128 | + Err(error) => { |
| 129 | + warn!("ONNX fake session unload failed: {}", error); |
| 130 | + return Ok(serde_json::to_value(UnserveModelResponse { |
| 131 | + success: true, |
| 132 | + error: Some("ONNX Runtime could not unload the selected model".to_string()), |
| 133 | + unloaded: false, |
| 134 | + snapshot: Some(state.api.get_serving_status().await?.snapshot), |
| 135 | + })?); |
| 136 | + } |
| 137 | + } |
| 138 | + |
| 139 | + let snapshot = state |
| 140 | + .api |
| 141 | + .record_unserved_model( |
| 142 | + &request.model_id, |
| 143 | + Some(RuntimeProviderId::OnnxRuntime), |
| 144 | + Some(&profile_id), |
| 145 | + Some(model_alias.as_str()), |
| 146 | + ) |
| 147 | + .await?; |
| 148 | + Ok(serde_json::to_value(UnserveModelResponse { |
| 149 | + success: true, |
| 150 | + error: None, |
| 151 | + unloaded: true, |
| 152 | + snapshot: Some(snapshot), |
| 153 | + })?) |
| 154 | +} |
| 155 | + |
| 156 | +async fn resolve_onnx_model_path( |
| 157 | + state: &AppState, |
| 158 | + request: &ServeModelRequest, |
| 159 | +) -> pumas_library::Result<Option<std::path::PathBuf>> { |
| 160 | + let library = state.api.model_library().clone(); |
| 161 | + let model_id = request.model_id.clone(); |
| 162 | + let primary_file = |
| 163 | + tokio::task::spawn_blocking(move || library.get_primary_model_file(&model_id)) |
| 164 | + .await |
| 165 | + .map_err(|err| { |
| 166 | + pumas_library::PumasError::Other(format!( |
| 167 | + "Failed to join primary ONNX model lookup task: {}", |
| 168 | + err |
| 169 | + )) |
| 170 | + })?; |
| 171 | + let Some(onnx_path) = primary_file else { |
| 172 | + return Ok(None); |
| 173 | + }; |
| 174 | + if ExecutableArtifactFormat::from_path(&onnx_path) != Some(ExecutableArtifactFormat::Onnx) { |
| 175 | + return Ok(None); |
| 176 | + } |
| 177 | + Ok(Some(onnx_path)) |
| 178 | +} |
0 commit comments