[Rust Frontend] Add dynamic LoRA endpoints (#43778)

Signed-off-by: xunzhuo <xunzhuo@vllm-semantic-router.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
Xunzhuo
2026-06-03 07:55:29 +00:00
committed by GitHub
co-authored by Bugen Zhao
parent 4aaed4ca22
commit 6550ff12f2
24 changed files with 1081 additions and 49 deletions
+1 -1
View File
@@ -40,11 +40,11 @@ pub fn lower_text_request(
cache_salt: request.cache_salt.clone(),
priority: request.priority,
data_parallel_rank: request.data_parallel_rank,
lora_request: request.lora_request.clone(),
// Fields below are currently placeholders.
arrival_time: None,
trace_headers: None,
reasoning_ended: None,
lora_request: None,
};
Ok(PreparedTextRequest {
+5
View File
@@ -4,6 +4,7 @@ use enum_as_inner::EnumAsInner;
use serde::{Deserialize, Serialize};
use serde_json::Value;
use vllm_engine_core_client::protocol::StructuredOutputsParams;
use vllm_engine_core_client::protocol::lora::LoraRequest;
use vllm_engine_core_client::protocol::multimodal::MmFeatures;
use crate::error::{Error, Result};
@@ -166,6 +167,9 @@ pub struct TextRequest {
/// Override data parallel rank.
#[serde(default)]
pub data_parallel_rank: Option<u32>,
/// LoRA adapter selected for this request.
#[serde(default)]
pub lora_request: Option<LoraRequest>,
}
impl TextRequest {
@@ -182,6 +186,7 @@ impl TextRequest {
cache_salt: None,
add_special_tokens: false,
data_parallel_rank: None,
lora_request: None,
}
}