[Rust Frontend] Split engine core DTOs into separate modules (#47265)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
@@ -1,8 +1,7 @@
|
||||
use axum::Json;
|
||||
use axum::http::StatusCode;
|
||||
use axum::response::{IntoResponse, Response};
|
||||
use thiserror_ext::AsReport as _;
|
||||
use thiserror_ext::{Construct, Macro};
|
||||
use thiserror_ext::{AsReport as _, Construct, Macro};
|
||||
|
||||
use crate::routes::openai::utils::types::{ErrorDetail, ErrorResponse};
|
||||
|
||||
|
||||
@@ -3,7 +3,8 @@
|
||||
|
||||
use tonic::Status;
|
||||
use uuid::Uuid;
|
||||
use vllm_engine_core_client::protocol::{StopReason, StructuredOutputsParams};
|
||||
use vllm_engine_core_client::protocol::output::StopReason;
|
||||
use vllm_engine_core_client::protocol::structured_outputs::StructuredOutputsParams;
|
||||
use vllm_text::{
|
||||
DecodedLogprobs, DecodedPromptLogprobs, FinishReason, Finished, Prompt, SamplingParams,
|
||||
TextDecodeOptions, TextRequest,
|
||||
@@ -502,7 +503,7 @@ impl ResponseOpts {
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use vllm_engine_core_client::protocol::StopReason;
|
||||
use vllm_engine_core_client::protocol::output::StopReason;
|
||||
use vllm_text::{FinishReason, Finished, Prompt};
|
||||
|
||||
use super::pb::finish_info::{FinishReason as PbFinishReason, StopReason as PbStopReason};
|
||||
|
||||
@@ -18,9 +18,10 @@ use vllm_chat::{
|
||||
ChatBackend, ChatLlm, ChatRenderer, ChatRequest, ChatTextBackend, DefaultChatOutputProcessor,
|
||||
DynChatOutputProcessor, DynChatRenderer, NewChatOutputProcessorOptions, RenderedPrompt,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::{
|
||||
EngineCoreFinishReason, EngineCoreOutput, EngineCoreOutputs, EngineCoreRequest,
|
||||
use vllm_engine_core_client::protocol::output::{
|
||||
EngineCoreFinishReason, EngineCoreOutput, EngineCoreOutputs,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::request::EngineCoreRequest;
|
||||
use vllm_engine_core_client::test_utils::{IpcNamespace, spawn_mock_engine_task};
|
||||
use vllm_engine_core_client::{EngineCoreClient, EngineCoreClientConfig, EngineId};
|
||||
use vllm_llm::Llm;
|
||||
|
||||
@@ -152,8 +152,8 @@ impl axum::serve::Listener for Listener {
|
||||
|
||||
/// Allow the unified listener to be adaptable to `tls_listener`.
|
||||
impl AsyncAccept for Listener {
|
||||
type Connection = ListenerIo;
|
||||
type Address = ListenerAddr;
|
||||
type Connection = ListenerIo;
|
||||
type Error = std::io::Error;
|
||||
|
||||
fn poll_accept(
|
||||
|
||||
@@ -57,9 +57,9 @@ where
|
||||
S::Error: Send + 'static,
|
||||
B: Send + 'static,
|
||||
{
|
||||
type Response = S::Response;
|
||||
type Error = S::Error;
|
||||
type Future = BoxFuture<'static, Result<Self::Response, Self::Error>>;
|
||||
type Response = S::Response;
|
||||
|
||||
fn poll_ready(&mut self, cx: &mut Context<'_>) -> Poll<Result<(), Self::Error>> {
|
||||
self.inner.poll_ready(cx)
|
||||
|
||||
@@ -18,9 +18,10 @@ use vllm_chat::{
|
||||
ChatBackend, ChatLlm, ChatRenderer, ChatRequest, ChatTextBackend, DefaultChatOutputProcessor,
|
||||
DynChatOutputProcessor, DynChatRenderer, NewChatOutputProcessorOptions, RenderedPrompt,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::{
|
||||
EngineCoreFinishReason, EngineCoreOutput, EngineCoreOutputs, EngineCoreRequest,
|
||||
use vllm_engine_core_client::protocol::output::{
|
||||
EngineCoreFinishReason, EngineCoreOutput, EngineCoreOutputs,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::request::EngineCoreRequest;
|
||||
use vllm_engine_core_client::test_utils::{IpcNamespace, spawn_mock_engine_task};
|
||||
use vllm_engine_core_client::{EngineCoreClient, EngineCoreClientConfig, EngineId};
|
||||
use vllm_llm::Llm;
|
||||
|
||||
@@ -21,7 +21,7 @@ use vllm_chat::{
|
||||
AssistantBlockKind, AssistantMessageExt as _, ChatEvent, ChatEventStream, ChatEventStreamTrait,
|
||||
CollectedAssistantMessage, FinishReason,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::StopReason;
|
||||
use vllm_engine_core_client::protocol::output::StopReason;
|
||||
|
||||
use self::convert::{ResponseOptions, prepare_chat_request};
|
||||
use crate::config::ApiServerOptions;
|
||||
@@ -825,7 +825,7 @@ mod tests {
|
||||
use vllm_chat::{
|
||||
AssistantBlockKind, AssistantContentBlock, AssistantToolCall, ChatEvent, FinishReason,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::StopReason;
|
||||
use vllm_engine_core_client::protocol::output::StopReason;
|
||||
use vllm_text::{DecodedLogprobs, DecodedPositionLogprobs, DecodedTokenLogprob};
|
||||
|
||||
use super::{
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::Value;
|
||||
use vllm_engine_core_client::protocol::StructuredOutputsParams;
|
||||
use vllm_engine_core_client::protocol::structured_outputs::StructuredOutputsParams;
|
||||
|
||||
use crate::error::ApiError;
|
||||
|
||||
|
||||
@@ -24,14 +24,15 @@ use vllm_chat::{
|
||||
NewChatOutputProcessorOptions,
|
||||
};
|
||||
use vllm_engine_core_client::mock_engine::default_ready_response;
|
||||
use vllm_engine_core_client::protocol::decode_value;
|
||||
use vllm_engine_core_client::protocol::logprobs::{
|
||||
Logprobs, MaybeWireLogprobs, PositionLogprobs, TokenLogprob,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::utility::{UtilityOutput, UtilityResultEnvelope};
|
||||
use vllm_engine_core_client::protocol::{
|
||||
EngineCoreFinishReason, EngineCoreOutput, EngineCoreOutputs, EngineCoreRequest, StopReason,
|
||||
decode_value,
|
||||
use vllm_engine_core_client::protocol::output::{
|
||||
EngineCoreFinishReason, EngineCoreOutput, EngineCoreOutputs, StopReason,
|
||||
};
|
||||
use vllm_engine_core_client::protocol::request::EngineCoreRequest;
|
||||
use vllm_engine_core_client::protocol::utility::{UtilityOutput, UtilityResultEnvelope};
|
||||
use vllm_engine_core_client::test_utils::{
|
||||
IpcNamespace, spawn_mock_engine_task, spawn_mock_engine_task_with_ready,
|
||||
};
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
use std::sync::Arc;
|
||||
use std::sync::OnceLock;
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
use std::sync::{Arc, OnceLock};
|
||||
|
||||
use serde_json::Value;
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
Reference in New Issue
Block a user