diff --git a/sgl-router/Cargo.toml b/sgl-router/Cargo.toml
index 3535f4e03..45db679e2 100644
--- a/sgl-router/Cargo.toml
+++ b/sgl-router/Cargo.toml
@@ -1,5 +1,5 @@
 [package]
-name = "sglang-router"
+name = "sgl-model-gateway"
 version = "0.2.3"
 edition = "2021"
 
@@ -11,12 +11,11 @@ vendored-openssl = ["openssl/vendored"]
 unused_qualifications = "warn"
 
 [lib]
-name = "sglang_router_rs"
-# Pure Rust library (rlib for the binary and other Rust dependents)
+name = "sgl_model_gateway"
 crate-type = ["rlib"]
 
 [[bin]]
-name = "sglang-router"
+name = "sgl-model-gateway"
 path = "src/main.rs"
 
 [[bin]]
diff --git a/sgl-router/README.md b/sgl-router/README.md
index 780df2444..a7b099978 100644
--- a/sgl-router/README.md
+++ b/sgl-router/README.md
@@ -93,20 +93,28 @@ pip install --force-reinstall dist/*.whl
 After installation, verify the installation and check version information:
 
 ```bash
-# Short version info (Rust binary)
-./target/release/sglang-router -v
+# Simple version (Rust binary)
+./target/release/sgl-model-gateway --version
+# or use aliases
+./target/release/smg --version
+./target/release/amg --version
 
-# Full version info with build details (Rust binary)
-./target/release/sglang-router --version
+# Full version info with build details
+./target/release/sgl-model-gateway --version-verbose
+
+# Python CLI
+amg --version
+amg --version-verbose
+python3 -m sglang_router --version
 ```
 
-The `-v` flag displays a concise version string, while `--version` (or `-V`) shows comprehensive build information including Git commit, build time, compiler versions, and platform details.
+The `--version` (or `-V`) flag displays the version string. Use `--version-verbose` for comprehensive build information including Git commit, build time, compiler versions, and platform details.
 
 ## Quick Start
 ### Regular HTTP Routing
 - **Rust binary**
   ```bash
-  ./target/release/sglang-router \
+  ./target/release/sgl-model-gateway \
     --worker-urls http://worker1:8000 http://worker2:8000 \
     --policy cache_aware
   ```
@@ -121,7 +129,7 @@ The `-v` flag displays a concise version string, while `--version` (or `-V`) sho
 ### Prefill/Decode Disaggregation (PD)
 - **Rust binary**
   ```bash
-  ./target/release/sglang-router \
+  ./target/release/sgl-model-gateway \
     --pd-disaggregation \
     --prefill http://prefill1:30001 9001 \
     --prefill http://prefill2:30002 \
@@ -146,7 +154,7 @@ Prefill entries accept an optional bootstrap port. PD mode merges prefill metada
 ### Multi-Model Inference Gateway
 Enable IGW mode to route multiple models through a single router while applying per-model policies:
 ```bash
-./target/release/sglang-router \
+./target/release/sgl-model-gateway \
   --enable-igw \
   --policy cache_aware \
   --max-concurrent-requests 512
@@ -194,7 +202,7 @@ Add more workers with the same API; include optional `labels` (for per-model pol
 ### gRPC Routing
 - **Rust binary**
   ```bash
-  ./target/release/sglang-router \
+  ./target/release/sgl-model-gateway \
     --worker-urls grpc://worker-grpc-0:31001 grpc://worker-grpc-1:31002 \
     --tokenizer-path /path/to/tokenizer.json \
     --reasoning-parser deepseek-r1 \
@@ -229,7 +237,7 @@ python3 -m sglang_router.launch_router \
 **Notes**
 - OpenAI backend mode acts as a proxy to a single remote endpoint; load balancing is not applied.
 - Provide exactly one `--worker-urls` entry per router instance.
-- The Rust binary supports the same flags (`./target/release/sglang-router --backend openai ...`).
+- The Rust binary supports the same flags (`./target/release/sgl-model-gateway --backend openai ...`).
 
 ### MCP Integration
 The SGL Model Gateway provides native Model Context Protocol (MCP) client integration, enabling tool calling across STDIO, SSE, and Streamable transports. MCP servers are configured via a YAML configuration file and registered at startup through the workflow engine.
@@ -237,7 +245,7 @@ The SGL Model Gateway provides native Model Context Protocol (MCP) client integr
 #### Basic Usage
 ```bash
 # Rust binary
-./target/release/sglang-router \
+./target/release/sgl-model-gateway \
   --mcp-config-path /path/to/mcp-config.yaml \
   --worker-urls http://worker1:8000
 
@@ -407,7 +415,7 @@ All administrative routes inherit router API-key protection when `--api-key` is
 ### Service Discovery
 Enable Kubernetes discovery to reconcile workers automatically:
 ```bash
-./target/release/sglang-router \
+./target/release/sgl-model-gateway \
   --service-discovery \
   --selector app=sglang-worker role=inference \
   --service-discovery-namespace sglang-system \
diff --git a/sgl-router/benches/request_processing.rs b/sgl-router/benches/request_processing.rs
index 54d704512..60d51faf0 100644
--- a/sgl-router/benches/request_processing.rs
+++ b/sgl-router/benches/request_processing.rs
@@ -2,7 +2,7 @@ use std::time::Instant;
 
 use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion, Throughput};
 use serde_json::{from_str, to_string, to_value, to_vec};
-use sglang_router_rs::{
+use sgl_model_gateway::{
     core::{BasicWorker, BasicWorkerBuilder, Worker, WorkerType},
     protocols::{
         chat::{ChatCompletionRequest, ChatMessage, MessageContent},
diff --git a/sgl-router/benches/tokenizer_benchmark.rs b/sgl-router/benches/tokenizer_benchmark.rs
index 1175bfb6a..c53ee300f 100644
--- a/sgl-router/benches/tokenizer_benchmark.rs
+++ b/sgl-router/benches/tokenizer_benchmark.rs
@@ -13,7 +13,7 @@ use std::{
 };
 
 use criterion::{black_box, criterion_group, BenchmarkId, Criterion, Throughput};
-use sglang_router_rs::tokenizer::{
+use sgl_model_gateway::tokenizer::{
     cache::{CacheConfig, CachedTokenizer},
     huggingface::HuggingFaceTokenizer,
     sequence::Sequence,
@@ -31,7 +31,7 @@ fn get_tokenizer_path() -> &'static PathBuf {
         // with special: true, normalized: false - perfect for demonstrating L1 cache
         let rt = tokio::runtime::Runtime::new().expect("Failed to create tokio runtime");
         let tokenizer_dir = rt.block_on(async {
-            sglang_router_rs::tokenizer::hub::download_tokenizer_from_hf(
+            sgl_model_gateway::tokenizer::hub::download_tokenizer_from_hf(
                 "Qwen/Qwen3-4B-Instruct-2507",
             )
             .await
diff --git a/sgl-router/benches/tool_parser_benchmark.rs b/sgl-router/benches/tool_parser_benchmark.rs
index 0e09bbd4c..30fd76f15 100644
--- a/sgl-router/benches/tool_parser_benchmark.rs
+++ b/sgl-router/benches/tool_parser_benchmark.rs
@@ -19,7 +19,7 @@ use std::{
 
 use criterion::{black_box, criterion_group, BenchmarkId, Criterion, Throughput};
 use serde_json::json;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     protocols::common::{Function, Tool},
     tool_parser::{JsonParser, ParserFactory as ToolParserFactory, ToolParser},
 };
diff --git a/sgl-router/bindings/golang/Cargo.toml b/sgl-router/bindings/golang/Cargo.toml
index eaedea36c..28f209050 100644
--- a/sgl-router/bindings/golang/Cargo.toml
+++ b/sgl-router/bindings/golang/Cargo.toml
@@ -1,10 +1,10 @@
 [package]
-name = "sglang-router-golang"
-version = "0.2.2"
+name = "sgl-model-gateway-golang"
+version = "0.2.3"
 edition = "2021"
 
 [lib]
-name = "sglang_router_rs"
+name = "sgl_model_gateway_go"
 crate-type = ["cdylib"]
 
 [dependencies]
@@ -18,14 +18,13 @@ once_cell = "1.21.3"
 futures-util = "0.3"
 tracing = "0.1"
 
-[dependencies.sglang-router]
+[dependencies.sgl-model-gateway]
 path = "../.."
 default-features = true
-package = "sglang-router"
 
 [features]
 default = []
-vendored-openssl = ["sglang-router/vendored-openssl"]
+vendored-openssl = ["sgl-model-gateway/vendored-openssl"]
 
 [profile.release]
 opt-level = "z"     # Optimize for size
diff --git a/sgl-router/bindings/golang/src/client.rs b/sgl-router/bindings/golang/src/client.rs
index 87543ecec..b4359567f 100644
--- a/sgl-router/bindings/golang/src/client.rs
+++ b/sgl-router/bindings/golang/src/client.rs
@@ -8,11 +8,11 @@ use tokio::runtime::Runtime;
 use once_cell::sync::Lazy;
 use uuid::Uuid;
 
-use sglang_router::tokenizer::create_tokenizer_from_file;
-use sglang_router::tokenizer::traits::Tokenizer;
-use sglang_router::grpc_client::sglang_scheduler::SglangSchedulerClient;
-use sglang_router::protocols::chat::ChatCompletionRequest;
-use sglang_router::routers::grpc::utils::{process_chat_messages, generate_tool_constraints};
+use sgl_model_gateway::tokenizer::create_tokenizer_from_file;
+use sgl_model_gateway::tokenizer::traits::Tokenizer;
+use sgl_model_gateway::grpc_client::sglang_scheduler::SglangSchedulerClient;
+use sgl_model_gateway::protocols::chat::ChatCompletionRequest;
+use sgl_model_gateway::routers::grpc::utils::{process_chat_messages, generate_tool_constraints};
 
 use super::error::{SglErrorCode, set_error_message};
 use super::grpc_converter::sgl_grpc_response_converter_create;
diff --git a/sgl-router/bindings/golang/src/grpc_converter.rs b/sgl-router/bindings/golang/src/grpc_converter.rs
index c8ec7ecf3..e808884b7 100644
--- a/sgl-router/bindings/golang/src/grpc_converter.rs
+++ b/sgl-router/bindings/golang/src/grpc_converter.rs
@@ -9,12 +9,12 @@ use serde_json::Value;
 use tokio::runtime::Runtime;
 use once_cell::sync::Lazy;
 
-use sglang_router::tokenizer::traits::Tokenizer;
-use sglang_router::tokenizer::stream::DecodeStream;
-use sglang_router::tool_parser::ToolParser;
-use sglang_router::protocols::common::{Tool, ToolChoice, ToolChoiceValue, ToolCallDelta, FunctionCallDelta, Usage, StringOrArray};
-use sglang_router::tokenizer::stop::StopSequenceDecoder;
-use sglang_router::grpc_client::sglang_proto as proto;
+use sgl_model_gateway::tokenizer::traits::Tokenizer;
+use sgl_model_gateway::tokenizer::stream::DecodeStream;
+use sgl_model_gateway::tool_parser::ToolParser;
+use sgl_model_gateway::protocols::common::{Tool, ToolChoice, ToolChoiceValue, ToolCallDelta, FunctionCallDelta, Usage, StringOrArray};
+use sgl_model_gateway::tokenizer::stop::StopSequenceDecoder;
+use sgl_model_gateway::grpc_client::sglang_proto as proto;
 
 use super::error::{SglErrorCode, set_error_message, clear_error_message};
 use super::tokenizer::TokenizerHandle;
@@ -22,9 +22,9 @@ use super::utils::generate_tool_call_id;
 
 /// Global parser factory (initialized once)
 // Use the re-exported ParserFactory from tool_parser module
-static PARSER_FACTORY: Lazy<sglang_router::tool_parser::ParserFactory> = Lazy::new(|| {
+static PARSER_FACTORY: Lazy<sgl_model_gateway::tool_parser::ParserFactory> = Lazy::new(|| {
     // ParserFactory is re-exported from tool_parser::factory, so we can use it directly
-    sglang_router::tool_parser::ParserFactory::default()
+    sgl_model_gateway::tool_parser::ParserFactory::default()
 });
 
 /// Global tokio runtime for async operations
@@ -151,7 +151,7 @@ pub unsafe extern "C" fn sgl_grpc_response_converter_create(
     // Create stop decoder if needed
     let stop_decoder = if stop.is_some() || stop_token_ids.is_some() {
         Some(Arc::new(tokio::sync::Mutex::new(
-            sglang_router::routers::grpc::utils::create_stop_decoder(
+            sgl_model_gateway::routers::grpc::utils::create_stop_decoder(
                 &tokenizer,
                 stop.as_ref(),
                 stop_token_ids.as_ref(),
@@ -389,9 +389,9 @@ pub(crate) async fn convert_proto_chunk_to_openai(
     request_id: &str,
     created: u64,
     system_fingerprint: Option<&str>,
-) -> Result<Option<sglang_router::protocols::chat::ChatCompletionStreamResponse>, String> {
-    use sglang_router::grpc_client::sglang_proto::generate_response::Response::*;
-    use sglang_router::protocols::chat::{ChatCompletionStreamResponse, ChatMessageDelta, ChatStreamChoice};
+) -> Result<Option<sgl_model_gateway::protocols::chat::ChatCompletionStreamResponse>, String> {
+    use sgl_model_gateway::grpc_client::sglang_proto::generate_response::Response::*;
+    use sgl_model_gateway::protocols::chat::{ChatCompletionStreamResponse, ChatMessageDelta, ChatStreamChoice};
 
     match proto_response.response {
         Some(Chunk(chunk)) => {
@@ -427,19 +427,19 @@ pub(crate) async fn convert_proto_chunk_to_openai(
                 let mut text = String::new();
                 for &token_id in &chunk.token_ids {
                     match decoder_guard.process_token(token_id).unwrap_or_else(|_| {
-                        sglang_router::tokenizer::stop::SequenceDecoderOutput::Held
+                        sgl_model_gateway::tokenizer::stop::SequenceDecoderOutput::Held
                     }) {
-                        sglang_router::tokenizer::stop::SequenceDecoderOutput::Text(t) => {
+                        sgl_model_gateway::tokenizer::stop::SequenceDecoderOutput::Text(t) => {
                             text.push_str(&t);
                         }
-                        sglang_router::tokenizer::stop::SequenceDecoderOutput::StoppedWithText(t) => {
+                        sgl_model_gateway::tokenizer::stop::SequenceDecoderOutput::StoppedWithText(t) => {
                             text.push_str(&t);
                             break;
                         }
-                        sglang_router::tokenizer::stop::SequenceDecoderOutput::Stopped => {
+                        sgl_model_gateway::tokenizer::stop::SequenceDecoderOutput::Stopped => {
                             break;
                         }
-                        sglang_router::tokenizer::stop::SequenceDecoderOutput::Held => {}
+                        sgl_model_gateway::tokenizer::stop::SequenceDecoderOutput::Held => {}
                     }
                 }
                 text
diff --git a/sgl-router/bindings/golang/src/stream.rs b/sgl-router/bindings/golang/src/stream.rs
index 8bd57ac6c..65cd32476 100644
--- a/sgl-router/bindings/golang/src/stream.rs
+++ b/sgl-router/bindings/golang/src/stream.rs
@@ -23,7 +23,7 @@ use tokio::runtime::Runtime;
 use once_cell::sync::Lazy;
 use futures_util::StreamExt;
 
-use sglang_router::grpc_client::{sglang_proto as proto, sglang_scheduler::{SglangSchedulerClient, AbortOnDropStream}};
+use sgl_model_gateway::grpc_client::{sglang_proto as proto, sglang_scheduler::{SglangSchedulerClient, AbortOnDropStream}};
 
 use super::error::{SglErrorCode, set_error_message};
 use super::grpc_converter::{GrpcResponseConverterHandle, convert_proto_chunk_to_openai};
diff --git a/sgl-router/bindings/golang/src/tokenizer.rs b/sgl-router/bindings/golang/src/tokenizer.rs
index 191054c29..567abefc8 100644
--- a/sgl-router/bindings/golang/src/tokenizer.rs
+++ b/sgl-router/bindings/golang/src/tokenizer.rs
@@ -6,7 +6,7 @@ use std::ptr;
 use std::sync::Arc;
 use serde_json::Value;
 
-use sglang_router::tokenizer::{
+use sgl_model_gateway::tokenizer::{
     create_tokenizer_from_file,
     traits::Tokenizer as TokenizerTrait,
     chat_template::ChatTemplateParams,
diff --git a/sgl-router/bindings/golang/src/tool_parser.rs b/sgl-router/bindings/golang/src/tool_parser.rs
index 1889ac162..49b2639a9 100644
--- a/sgl-router/bindings/golang/src/tool_parser.rs
+++ b/sgl-router/bindings/golang/src/tool_parser.rs
@@ -9,8 +9,8 @@ use serde_json::{json, Value};
 use tokio::runtime::Runtime;
 use once_cell::sync::Lazy;
 
-use sglang_router::tool_parser::{ParserFactory, ToolParser};
-use sglang_router::protocols::common::Tool;
+use sgl_model_gateway::tool_parser::{ParserFactory, ToolParser};
+use sgl_model_gateway::protocols::common::Tool;
 
 use super::error::{SglErrorCode, set_error_message, clear_error_message};
 use super::utils::generate_tool_call_id;
diff --git a/sgl-router/bindings/python/Cargo.toml b/sgl-router/bindings/python/Cargo.toml
index d2054d76d..68f73fd14 100644
--- a/sgl-router/bindings/python/Cargo.toml
+++ b/sgl-router/bindings/python/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
-name = "sglang-router-python"
-version = "0.2.2"
+name = "sgl-model-gateway-python"
+version = "0.2.3"
 edition = "2021"
 
 [lib]
@@ -11,14 +11,13 @@ crate-type = ["cdylib"]
 pyo3 = { version = "0.27.1", features = ["extension-module", "abi3-py38"] }
 tokio = { version = "1.42.0", features = ["full"] }
 
-[dependencies.sglang-router]
+[dependencies.sgl-model-gateway]
 path = "../.."
 default-features = true
-package = "sglang-router"
 
 [features]
 default = ["pyo3/extension-module"]
-vendored-openssl = ["sglang-router/vendored-openssl"]
+vendored-openssl = ["sgl-model-gateway/vendored-openssl"]
 
 [profile.ci]
 inherits = "release"
diff --git a/sgl-router/bindings/python/src/lib.rs b/sgl-router/bindings/python/src/lib.rs
index 16e5c225b..8a321cc95 100644
--- a/sgl-router/bindings/python/src/lib.rs
+++ b/sgl-router/bindings/python/src/lib.rs
@@ -1,5 +1,5 @@
 use pyo3::prelude::*;
-use sglang_router::*;
+use sgl_model_gateway::*;
 use std::collections::HashMap;
 
 // Define the enums with PyO3 bindings
diff --git a/sgl-router/src/core/model_card.rs b/sgl-router/src/core/model_card.rs
index a2c27360d..f1d31bcb7 100644
--- a/sgl-router/src/core/model_card.rs
+++ b/sgl-router/src/core/model_card.rs
@@ -90,7 +90,7 @@ impl std::fmt::Display for ProviderType {
 /// # Example
 ///
 /// ```
-/// use sglang_router_rs::core::{ModelCard, ModelType, ProviderType};
+/// use sgl_model_gateway::core::{ModelCard, ModelType, ProviderType};
 ///
 /// let card = ModelCard::new("meta-llama/Llama-3.1-8B-Instruct")
 ///     .with_display_name("Llama 3.1 8B Instruct")
diff --git a/sgl-router/src/logging.rs b/sgl-router/src/logging.rs
index 7590e9e15..674149274 100644
--- a/sgl-router/src/logging.rs
+++ b/sgl-router/src/logging.rs
@@ -28,7 +28,7 @@ impl Default for LoggingConfig {
             log_dir: None,
             colorize: true,
             log_file_name: "sgl-router".to_string(),
-            log_targets: Some(vec!["sglang_router_rs".to_string()]),
+            log_targets: Some(vec!["sgl_model_gateway".to_string()]),
         }
     }
 }
@@ -63,7 +63,7 @@ pub fn init_logging(config: LoggingConfig) -> LogGuard {
                 })
                 .collect::<String>()
         } else {
-            format!("sglang_router_rs={}", level_filter)
+            format!("sgl_model_gateway={}", level_filter)
         };
 
         EnvFilter::new(filter_string)
diff --git a/sgl-router/src/main.rs b/sgl-router/src/main.rs
index 2ea5ee82a..87b39aa19 100644
--- a/sgl-router/src/main.rs
+++ b/sgl-router/src/main.rs
@@ -1,7 +1,7 @@
 use std::collections::HashMap;
 
 use clap::{ArgAction, Parser, Subcommand, ValueEnum};
-use sglang_router_rs::{
+use sgl_model_gateway::{
     config::{
         CircuitBreakerConfig, ConfigError, ConfigResult, DiscoveryConfig, HealthCheckConfig,
         HistoryBackend, MetricsConfig, OracleConfig, PolicyConfig, PostgresConfig, RetryConfig,
diff --git a/sgl-router/src/middleware.rs b/sgl-router/src/middleware.rs
index e9fb86220..e4811b1ef 100644
--- a/sgl-router/src/middleware.rs
+++ b/sgl-router/src/middleware.rs
@@ -222,7 +222,7 @@ impl<B> OnRequest<B> for RequestLogger {
 
         // Log the request start
         info!(
-            target: "sglang_router_rs::request",
+            target: "sgl_model_gateway::request",
             "started processing request"
         );
     }
@@ -254,17 +254,17 @@ impl<B> OnResponse<B> for ResponseLogger {
         let _enter = span.enter();
         if status.is_server_error() {
             error!(
-                target: "sglang_router_rs::response",
+                target: "sgl_model_gateway::response",
                 "request failed with server error"
             );
         } else if status.is_client_error() {
             warn!(
-                target: "sglang_router_rs::response",
+                target: "sgl_model_gateway::response",
                 "request failed with client error"
             );
         } else {
             info!(
-                target: "sglang_router_rs::response",
+                target: "sgl_model_gateway::response",
                 "finished processing request"
             );
         }
@@ -303,7 +303,7 @@ pub struct RequestLogEntry {
 pub fn log_request(entry: RequestLogEntry) {
     if entry.status >= 500 {
         tracing::error!(
-            target: "sglang_router_rs::http",
+            target: "sgl_model_gateway::http",
             request_id = %entry.request_id,
             method = %entry.method,
             uri = %entry.uri,
@@ -316,7 +316,7 @@ pub fn log_request(entry: RequestLogEntry) {
         );
     } else if entry.status >= 400 {
         tracing::warn!(
-            target: "sglang_router_rs::http",
+            target: "sgl_model_gateway::http",
             request_id = %entry.request_id,
             method = %entry.method,
             uri = %entry.uri,
@@ -328,7 +328,7 @@ pub fn log_request(entry: RequestLogEntry) {
         );
     } else {
         tracing::info!(
-            target: "sglang_router_rs::http",
+            target: "sgl_model_gateway::http",
             request_id = %entry.request_id,
             method = %entry.method,
             uri = %entry.uri,
diff --git a/sgl-router/src/routers/grpc/harmony/mod.rs b/sgl-router/src/routers/grpc/harmony/mod.rs
index 772dca357..58f45756d 100644
--- a/sgl-router/src/routers/grpc/harmony/mod.rs
+++ b/sgl-router/src/routers/grpc/harmony/mod.rs
@@ -18,7 +18,7 @@
 //! ## Usage
 //!
 //! ```ignore
-//! use sglang_router_rs::routers::grpc::harmony::{HarmonyDetector, HarmonyBuilder};
+//! use sgl_model_gateway::routers::grpc::harmony::{HarmonyDetector, HarmonyBuilder};
 //!
 //! // Detect if model supports Harmony
 //! if HarmonyDetector::is_harmony_model("gpt-4o") {
diff --git a/sgl-router/src/tokenizer/README.md b/sgl-router/src/tokenizer/README.md
index 49ea3aa34..2a4b7a3d5 100644
--- a/sgl-router/src/tokenizer/README.md
+++ b/sgl-router/src/tokenizer/README.md
@@ -138,7 +138,7 @@ as of `sgl-router/src/tokenizer/*`.
 ## Usage Examples
 ```rust
 use std::sync::Arc;
-use sglang_router_rs::tokenizer::{
+use sgl_model_gateway::tokenizer::{
     create_tokenizer, SequenceDecoderOutput, StopSequenceDecoderBuilder, Tokenizer,
 };
 
@@ -172,7 +172,7 @@ for &token in encoding.token_ids() {
 
 ```rust
 // Apply a chat template when one is bundled with the tokenizer
-use sglang_router_rs::tokenizer::{chat_template::ChatTemplateParams, HuggingFaceTokenizer};
+use sgl_model_gateway::tokenizer::{chat_template::ChatTemplateParams, HuggingFaceTokenizer};
 
 let mut hf = HuggingFaceTokenizer::from_file_with_chat_template(
     "./tokenizer.json",
diff --git a/sgl-router/tests/api_endpoints_test.rs b/sgl-router/tests/api_endpoints_test.rs
index ac4c93e21..8318cafba 100644
--- a/sgl-router/tests/api_endpoints_test.rs
+++ b/sgl-router/tests/api_endpoints_test.rs
@@ -10,7 +10,7 @@ use axum::{
 use common::mock_worker::{HealthStatus, MockWorker, MockWorkerConfig, WorkerType};
 use reqwest::Client;
 use serde_json::json;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     app_context::AppContext,
     config::{RouterConfig, RoutingMode},
     core::Job,
@@ -1028,7 +1028,7 @@ mod responses_endpoint_tests {
         let app = ctx.create_app().await;
 
         // Directly store a response in the storage to test the retrieval endpoint
-        use sglang_router_rs::data_connector::{ResponseId, StoredResponse};
+        use sgl_model_gateway::data_connector::{ResponseId, StoredResponse};
         let mut stored_response = StoredResponse::new(None);
         stored_response.id = ResponseId::from("resp_test_input_items");
         stored_response.input = json!([
diff --git a/sgl-router/tests/cache_aware_backward_compat_test.rs b/sgl-router/tests/cache_aware_backward_compat_test.rs
index 9cafd6240..6e45fc372 100644
--- a/sgl-router/tests/cache_aware_backward_compat_test.rs
+++ b/sgl-router/tests/cache_aware_backward_compat_test.rs
@@ -1,6 +1,6 @@
 use std::{collections::HashMap, sync::Arc};
 
-use sglang_router_rs::{
+use sgl_model_gateway::{
     core::{BasicWorkerBuilder, Worker, WorkerType},
     policies::{CacheAwareConfig, CacheAwarePolicy, LoadBalancingPolicy},
 };
diff --git a/sgl-router/tests/chat_template_format_detection.rs b/sgl-router/tests/chat_template_format_detection.rs
index 2e233533d..519047e37 100644
--- a/sgl-router/tests/chat_template_format_detection.rs
+++ b/sgl-router/tests/chat_template_format_detection.rs
@@ -1,4 +1,4 @@
-use sglang_router_rs::{
+use sgl_model_gateway::{
     protocols::chat::{ChatMessage, MessageContent},
     tokenizer::chat_template::{
         detect_chat_template_content_format, ChatTemplateContentFormat, ChatTemplateParams,
diff --git a/sgl-router/tests/chat_template_integration.rs b/sgl-router/tests/chat_template_integration.rs
index 805175755..165a01228 100644
--- a/sgl-router/tests/chat_template_integration.rs
+++ b/sgl-router/tests/chat_template_integration.rs
@@ -1,4 +1,4 @@
-use sglang_router_rs::{
+use sgl_model_gateway::{
     protocols::{
         chat::{ChatMessage, MessageContent},
         common::{ContentPart, ImageUrl},
diff --git a/sgl-router/tests/chat_template_loading.rs b/sgl-router/tests/chat_template_loading.rs
index 428101565..945f1506f 100644
--- a/sgl-router/tests/chat_template_loading.rs
+++ b/sgl-router/tests/chat_template_loading.rs
@@ -2,7 +2,7 @@
 mod tests {
     use std::fs;
 
-    use sglang_router_rs::{
+    use sgl_model_gateway::{
         protocols::chat::{ChatMessage, MessageContent},
         tokenizer::{chat_template::ChatTemplateParams, huggingface::HuggingFaceTokenizer},
     };
@@ -78,7 +78,7 @@ mod tests {
             .map(|msg| serde_json::to_value(msg).unwrap())
             .collect();
 
-        use sglang_router_rs::tokenizer::chat_template::ChatTemplateParams;
+        use sgl_model_gateway::tokenizer::chat_template::ChatTemplateParams;
         let params = ChatTemplateParams {
             add_generation_prompt: true,
             ..Default::default()
diff --git a/sgl-router/tests/common/mod.rs b/sgl-router/tests/common/mod.rs
index 4822b34b4..aa3893fb2 100644
--- a/sgl-router/tests/common/mod.rs
+++ b/sgl-router/tests/common/mod.rs
@@ -14,7 +14,7 @@ use std::{
 };
 
 use serde_json::json;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     app_context::AppContext,
     config::RouterConfig,
     core::{LoadMonitor, WorkerRegistry},
@@ -90,8 +90,8 @@ pub async fn create_test_context(config: RouterConfig) -> Arc<AppContext> {
 
     // Initialize JobQueue after AppContext is created
     let weak_context = Arc::downgrade(&app_context);
-    let job_queue = sglang_router_rs::core::JobQueue::new(
-        sglang_router_rs::core::JobQueueConfig::default(),
+    let job_queue = sgl_model_gateway::core::JobQueue::new(
+        sgl_model_gateway::core::JobQueueConfig::default(),
         weak_context,
     );
     app_context
@@ -100,7 +100,7 @@ pub async fn create_test_context(config: RouterConfig) -> Arc<AppContext> {
         .expect("JobQueue should only be initialized once");
 
     // Initialize WorkflowEngine and register workflows
-    use sglang_router_rs::core::workflow::{
+    use sgl_model_gateway::core::workflow::{
         create_worker_registration_workflow, create_worker_removal_workflow, WorkflowEngine,
     };
     let engine = Arc::new(WorkflowEngine::new());
@@ -112,7 +112,7 @@ pub async fn create_test_context(config: RouterConfig) -> Arc<AppContext> {
         .expect("WorkflowEngine should only be initialized once");
 
     // Initialize MCP manager with empty config
-    use sglang_router_rs::mcp::{McpConfig, McpManager};
+    use sgl_model_gateway::mcp::{McpConfig, McpManager};
     let empty_config = McpConfig {
         servers: vec![],
         pool: Default::default(),
@@ -137,7 +137,7 @@ pub async fn create_test_context_with_mcp_config(
     config: RouterConfig,
     mcp_config_path: &str,
 ) -> Arc<AppContext> {
-    use sglang_router_rs::mcp::{McpConfig, McpManager};
+    use sgl_model_gateway::mcp::{McpConfig, McpManager};
 
     let client = reqwest::Client::new();
 
@@ -201,8 +201,8 @@ pub async fn create_test_context_with_mcp_config(
 
     // Initialize JobQueue after AppContext is created
     let weak_context = Arc::downgrade(&app_context);
-    let job_queue = sglang_router_rs::core::JobQueue::new(
-        sglang_router_rs::core::JobQueueConfig::default(),
+    let job_queue = sgl_model_gateway::core::JobQueue::new(
+        sgl_model_gateway::core::JobQueueConfig::default(),
         weak_context,
     );
     app_context
@@ -211,7 +211,7 @@ pub async fn create_test_context_with_mcp_config(
         .expect("JobQueue should only be initialized once");
 
     // Initialize WorkflowEngine and register workflows
-    use sglang_router_rs::core::workflow::{
+    use sgl_model_gateway::core::workflow::{
         create_worker_registration_workflow, create_worker_removal_workflow, WorkflowEngine,
     };
     let engine = Arc::new(WorkflowEngine::new());
diff --git a/sgl-router/tests/common/test_app.rs b/sgl-router/tests/common/test_app.rs
index 4cc2f6671..2fbb8c74b 100644
--- a/sgl-router/tests/common/test_app.rs
+++ b/sgl-router/tests/common/test_app.rs
@@ -2,7 +2,7 @@ use std::sync::{Arc, OnceLock};
 
 use axum::Router;
 use reqwest::Client;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     app_context::AppContext,
     config::RouterConfig,
     core::{LoadMonitor, WorkerRegistry},
diff --git a/sgl-router/tests/mcp_test.rs b/sgl-router/tests/mcp_test.rs
index 4254d48cb..8ab50d26d 100644
--- a/sgl-router/tests/mcp_test.rs
+++ b/sgl-router/tests/mcp_test.rs
@@ -13,7 +13,7 @@ use std::collections::HashMap;
 
 use common::mock_mcp_server::MockMCPServer;
 use serde_json::json;
-use sglang_router_rs::mcp::{McpConfig, McpError, McpManager, McpServerConfig, McpTransport};
+use sgl_model_gateway::mcp::{McpConfig, McpError, McpManager, McpServerConfig, McpTransport};
 
 /// Create a new mock server for testing (each test gets its own)
 async fn create_mock_server() -> MockMCPServer {
diff --git a/sgl-router/tests/metrics_aggregator_test.rs b/sgl-router/tests/metrics_aggregator_test.rs
index b8797180f..f019efa7c 100644
--- a/sgl-router/tests/metrics_aggregator_test.rs
+++ b/sgl-router/tests/metrics_aggregator_test.rs
@@ -1,4 +1,4 @@
-use sglang_router_rs::core::metrics_aggregator::{aggregate_metrics, MetricPack};
+use sgl_model_gateway::core::metrics_aggregator::{aggregate_metrics, MetricPack};
 
 #[test]
 fn test_aggregate_simple() {
diff --git a/sgl-router/tests/policy_registry_integration.rs b/sgl-router/tests/policy_registry_integration.rs
index 6926707be..5e3f54bd3 100644
--- a/sgl-router/tests/policy_registry_integration.rs
+++ b/sgl-router/tests/policy_registry_integration.rs
@@ -2,7 +2,7 @@
 
 use std::{collections::HashMap, sync::Arc};
 
-use sglang_router_rs::{
+use sgl_model_gateway::{
     config::PolicyConfig, core::WorkerRegistry, policies::PolicyRegistry,
     protocols::worker_spec::WorkerConfigRequest, routers::router_manager::RouterManager,
 };
@@ -115,7 +115,7 @@ async fn test_policy_registry_with_router_manager() {
 
 #[test]
 fn test_policy_registry_cleanup() {
-    use sglang_router_rs::{config::PolicyConfig, policies::PolicyRegistry};
+    use sgl_model_gateway::{config::PolicyConfig, policies::PolicyRegistry};
 
     let registry = PolicyRegistry::new(PolicyConfig::RoundRobin);
 
@@ -142,7 +142,7 @@ fn test_policy_registry_cleanup() {
 
 #[test]
 fn test_policy_registry_multiple_models() {
-    use sglang_router_rs::{config::PolicyConfig, policies::PolicyRegistry};
+    use sgl_model_gateway::{config::PolicyConfig, policies::PolicyRegistry};
 
     let registry = PolicyRegistry::new(PolicyConfig::RoundRobin);
 
diff --git a/sgl-router/tests/request_formats_test.rs b/sgl-router/tests/request_formats_test.rs
index e7e40b78d..2475bef6f 100644
--- a/sgl-router/tests/request_formats_test.rs
+++ b/sgl-router/tests/request_formats_test.rs
@@ -5,7 +5,7 @@ use std::sync::Arc;
 use common::mock_worker::{HealthStatus, MockWorker, MockWorkerConfig, WorkerType};
 use reqwest::Client;
 use serde_json::json;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     config::{RouterConfig, RoutingMode},
     routers::{RouterFactory, RouterTrait},
 };
diff --git a/sgl-router/tests/responses_api_test.rs b/sgl-router/tests/responses_api_test.rs
index beed0669c..31285868a 100644
--- a/sgl-router/tests/responses_api_test.rs
+++ b/sgl-router/tests/responses_api_test.rs
@@ -1,7 +1,7 @@
 // Integration test for Responses API
 
 use axum::http::StatusCode;
-use sglang_router_rs::protocols::{
+use sgl_model_gateway::protocols::{
     common::{GenerationRequest, ToolChoice, ToolChoiceValue, UsageInfo},
     responses::{
         ReasoningEffort, ResponseInput, ResponseReasoningParam, ResponseTool, ResponseToolType,
@@ -14,7 +14,7 @@ use common::{
     mock_mcp_server::MockMCPServer,
     mock_worker::{HealthStatus, MockWorker, MockWorkerConfig, WorkerType},
 };
-use sglang_router_rs::{config::RouterConfig, routers::RouterFactory};
+use sgl_model_gateway::{config::RouterConfig, routers::RouterFactory};
 
 #[tokio::test]
 async fn test_non_streaming_mcp_minimal_e2e_with_persistence() {
@@ -393,7 +393,7 @@ fn test_usage_conversion() {
         completion_tokens: 25,
         total_tokens: 40,
         reasoning_tokens: Some(8),
-        prompt_tokens_details: Some(sglang_router_rs::protocols::common::PromptTokenUsageInfo {
+        prompt_tokens_details: Some(sgl_model_gateway::protocols::common::PromptTokenUsageInfo {
             cached_tokens: 3,
         }),
     };
@@ -781,7 +781,7 @@ async fn test_max_tool_calls_limit() {
 async fn setup_streaming_mcp_test() -> (
     MockMCPServer,
     MockWorker,
-    Box<dyn sglang_router_rs::routers::RouterTrait>,
+    Box<dyn sgl_model_gateway::routers::RouterTrait>,
     tempfile::TempDir,
 ) {
     let mcp = MockMCPServer::start().await.expect("start mcp");
diff --git a/sgl-router/tests/spec/chat_completion.rs b/sgl-router/tests/spec/chat_completion.rs
index 3b30c1850..eaef324a4 100644
--- a/sgl-router/tests/spec/chat_completion.rs
+++ b/sgl-router/tests/spec/chat_completion.rs
@@ -1,5 +1,5 @@
 use serde_json::json;
-use sglang_router_rs::protocols::{
+use sgl_model_gateway::protocols::{
     chat::{ChatCompletionRequest, ChatMessage, MessageContent},
     common::{
         Function, FunctionCall, FunctionChoice, StreamOptions, Tool, ToolChoice, ToolChoiceValue,
diff --git a/sgl-router/tests/spec/chat_message.rs b/sgl-router/tests/spec/chat_message.rs
index 5aeaf1b14..539c12d9c 100644
--- a/sgl-router/tests/spec/chat_message.rs
+++ b/sgl-router/tests/spec/chat_message.rs
@@ -1,5 +1,5 @@
 use serde_json::json;
-use sglang_router_rs::protocols::chat::{ChatMessage, MessageContent};
+use sgl_model_gateway::protocols::chat::{ChatMessage, MessageContent};
 
 #[test]
 fn test_chat_message_tagged_by_role_system() {
diff --git a/sgl-router/tests/spec/embedding.rs b/sgl-router/tests/spec/embedding.rs
index 2a55d88af..af26ba679 100644
--- a/sgl-router/tests/spec/embedding.rs
+++ b/sgl-router/tests/spec/embedding.rs
@@ -1,5 +1,5 @@
 use serde_json::{from_str, json, to_string};
-use sglang_router_rs::protocols::{common::GenerationRequest, embedding::EmbeddingRequest};
+use sgl_model_gateway::protocols::{common::GenerationRequest, embedding::EmbeddingRequest};
 
 #[test]
 fn test_embedding_request_serialization_string_input() {
diff --git a/sgl-router/tests/spec/rerank.rs b/sgl-router/tests/spec/rerank.rs
index 3f6524a0c..4a40990d3 100644
--- a/sgl-router/tests/spec/rerank.rs
+++ b/sgl-router/tests/spec/rerank.rs
@@ -1,7 +1,7 @@
 use std::collections::HashMap;
 
 use serde_json::{from_str, to_string, Number, Value};
-use sglang_router_rs::protocols::{
+use sgl_model_gateway::protocols::{
     common::{GenerationRequest, StringOrArray, UsageInfo},
     rerank::{RerankRequest, RerankResponse, RerankResult, V1RerankReqInput},
 };
diff --git a/sgl-router/tests/spec/responses.rs b/sgl-router/tests/spec/responses.rs
index 8814c12e7..eab839c20 100644
--- a/sgl-router/tests/spec/responses.rs
+++ b/sgl-router/tests/spec/responses.rs
@@ -1,5 +1,5 @@
 use serde_json::json;
-use sglang_router_rs::protocols::{
+use sgl_model_gateway::protocols::{
     common::{Function, StringOrArray, ToolChoice, ToolChoiceValue},
     responses::{
         IncludeField, ResponseInput, ResponseInputOutputItem, ResponseTool, ResponseToolType,
@@ -963,7 +963,7 @@ fn test_validate_input_items_structure() {
 /// Test tool_choice defaults to auto when tools are present
 #[test]
 fn test_normalize_tool_choice_auto() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1004,7 +1004,7 @@ fn test_normalize_tool_choice_auto() {
 /// Test tool_choice defaults to none when tools array is empty
 #[test]
 fn test_normalize_tool_choice_none() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1031,7 +1031,7 @@ fn test_normalize_tool_choice_none() {
 /// Test tool_choice is not overridden if already set
 #[test]
 fn test_normalize_tool_choice_no_override() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1068,7 +1068,7 @@ fn test_normalize_tool_choice_no_override() {
 /// Test parallel_tool_calls defaults to true when tools are present
 #[test]
 fn test_normalize_parallel_tool_calls() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1107,7 +1107,7 @@ fn test_normalize_parallel_tool_calls() {
 /// Test parallel_tool_calls is not set when tools are absent
 #[test]
 fn test_normalize_parallel_tool_calls_no_tools() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1127,7 +1127,7 @@ fn test_normalize_parallel_tool_calls_no_tools() {
 /// Test parallel_tool_calls is not overridden if already set
 #[test]
 fn test_normalize_parallel_tool_calls_no_override() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1162,7 +1162,7 @@ fn test_normalize_parallel_tool_calls_no_override() {
 /// Test store defaults to true
 #[test]
 fn test_normalize_store_default() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
@@ -1182,7 +1182,7 @@ fn test_normalize_store_default() {
 /// Test store is not overridden if already set
 #[test]
 fn test_normalize_store_no_override() {
-    use sglang_router_rs::protocols::validated::Normalizable;
+    use sgl_model_gateway::protocols::validated::Normalizable;
 
     let mut request = ResponsesRequest {
         input: ResponseInput::Text("test".to_string()),
diff --git a/sgl-router/tests/streaming_tests.rs b/sgl-router/tests/streaming_tests.rs
index 701f218b1..cbcacff11 100644
--- a/sgl-router/tests/streaming_tests.rs
+++ b/sgl-router/tests/streaming_tests.rs
@@ -6,7 +6,7 @@ use common::mock_worker::{HealthStatus, MockWorker, MockWorkerConfig, WorkerType
 use futures_util::StreamExt;
 use reqwest::Client;
 use serde_json::json;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     config::{RouterConfig, RoutingMode},
     routers::{RouterFactory, RouterTrait},
 };
diff --git a/sgl-router/tests/test_openai_routing.rs b/sgl-router/tests/test_openai_routing.rs
index 8e7756011..6c24f9bf2 100644
--- a/sgl-router/tests/test_openai_routing.rs
+++ b/sgl-router/tests/test_openai_routing.rs
@@ -17,7 +17,7 @@ use axum::{
     Json, Router,
 };
 use serde_json::json;
-use sglang_router_rs::{
+use sgl_model_gateway::{
     config::{
         ConfigError, ConfigValidator, HistoryBackend, OracleConfig, RouterConfig, RoutingMode,
     },
@@ -577,12 +577,14 @@ async fn test_router_factory_openai_mode() {
         worker_urls: vec!["https://api.openai.com".to_string()],
     };
 
-    let router_config =
-        RouterConfig::new(routing_mode, sglang_router_rs::config::PolicyConfig::Random);
+    let router_config = RouterConfig::new(
+        routing_mode,
+        sgl_model_gateway::config::PolicyConfig::Random,
+    );
 
     let app_context = common::create_test_context(router_config).await;
 
-    let router = sglang_router_rs::routers::RouterFactory::create_router(&app_context).await;
+    let router = sgl_model_gateway::routers::RouterFactory::create_router(&app_context).await;
     assert!(
         router.is_ok(),
         "Router factory should create OpenAI router successfully"
diff --git a/sgl-router/tests/test_pd_routing.rs b/sgl-router/tests/test_pd_routing.rs
index 1151e144b..f26049f70 100644
--- a/sgl-router/tests/test_pd_routing.rs
+++ b/sgl-router/tests/test_pd_routing.rs
@@ -1,7 +1,7 @@
 #[cfg(test)]
 mod test_pd_routing {
     use serde_json::json;
-    use sglang_router_rs::{
+    use sgl_model_gateway::{
         app_context::AppContext,
         config::{PolicyConfig, RouterConfig, RoutingMode},
         core::{BasicWorkerBuilder, Worker, WorkerType},
@@ -38,7 +38,7 @@ mod test_pd_routing {
 
     #[test]
     fn test_worker_types() {
-        use sglang_router_rs::core::{BasicWorkerBuilder, Worker, WorkerType};
+        use sgl_model_gateway::core::{BasicWorkerBuilder, Worker, WorkerType};
 
         let prefill_worker: Box<dyn Worker> = Box::new(
             BasicWorkerBuilder::new("http://prefill:8080")
@@ -214,7 +214,7 @@ mod test_pd_routing {
             let app_context = {
                 use std::sync::{Arc, OnceLock};
 
-                use sglang_router_rs::{
+                use sgl_model_gateway::{
                     core::{LoadMonitor, WorkerRegistry},
                     data_connector::{
                         MemoryConversationItemStorage, MemoryConversationStorage,
@@ -673,7 +673,7 @@ mod test_pd_routing {
 
     #[test]
     fn test_bootstrap_injection_with_benchmark_requests() {
-        use sglang_router_rs::core::{BasicWorkerBuilder, Worker, WorkerType};
+        use sgl_model_gateway::core::{BasicWorkerBuilder, Worker, WorkerType};
 
         let mut benchmark_request = json!({
             "input_ids": vec![vec![1, 2, 3, 4]; 16], // Batch size 16
diff --git a/sgl-router/tests/tokenizer_cache_correctness_test.rs b/sgl-router/tests/tokenizer_cache_correctness_test.rs
index 66a1838fe..eef0d2d55 100644
--- a/sgl-router/tests/tokenizer_cache_correctness_test.rs
+++ b/sgl-router/tests/tokenizer_cache_correctness_test.rs
@@ -9,7 +9,7 @@ use std::{
     sync::{Arc, OnceLock},
 };
 
-use sglang_router_rs::tokenizer::{
+use sgl_model_gateway::tokenizer::{
     cache::{CacheConfig, CachedTokenizer},
     hub::download_tokenizer_from_hf,
     huggingface::HuggingFaceTokenizer,
diff --git a/sgl-router/tests/tokenizer_integration.rs b/sgl-router/tests/tokenizer_integration.rs
index b6fb68232..b88943e4b 100644
--- a/sgl-router/tests/tokenizer_integration.rs
+++ b/sgl-router/tests/tokenizer_integration.rs
@@ -7,7 +7,7 @@ mod common;
 use std::sync::Arc;
 
 use common::{ensure_tokenizer_cached, EXPECTED_HASHES, TEST_PROMPTS};
-use sglang_router_rs::tokenizer::{
+use sgl_model_gateway::tokenizer::{
     factory, huggingface::HuggingFaceTokenizer, sequence::Sequence, stop::*, stream::DecodeStream,
     traits::*,
 };
@@ -269,7 +269,7 @@ fn test_batch_encoding() {
 
 #[test]
 fn test_special_tokens() {
-    use sglang_router_rs::tokenizer::traits::Tokenizer as TokenizerTrait;
+    use sgl_model_gateway::tokenizer::traits::Tokenizer as TokenizerTrait;
 
     let tokenizer_path = ensure_tokenizer_cached();
     let tokenizer = HuggingFaceTokenizer::from_file(tokenizer_path.to_str().unwrap())
@@ -398,7 +398,7 @@ fn test_load_chat_template_from_local_file() {
 
 #[tokio::test]
 async fn test_tinyllama_embedded_template() {
-    use sglang_router_rs::tokenizer::hub::download_tokenizer_from_hf;
+    use sgl_model_gateway::tokenizer::hub::download_tokenizer_from_hf;
 
     // Skip in CI without HF_TOKEN
 
@@ -434,7 +434,7 @@ async fn test_tinyllama_embedded_template() {
 
 #[tokio::test]
 async fn test_qwen3_next_embedded_template() {
-    use sglang_router_rs::tokenizer::hub::download_tokenizer_from_hf;
+    use sgl_model_gateway::tokenizer::hub::download_tokenizer_from_hf;
 
     // Test 3: Qwen3-Next has chat template in tokenizer_config.json
     match download_tokenizer_from_hf("Qwen/Qwen3-Next-80B-A3B-Instruct").await {
@@ -466,7 +466,7 @@ async fn test_qwen3_next_embedded_template() {
 
 #[tokio::test]
 async fn test_qwen3_vl_json_template_priority() {
-    use sglang_router_rs::tokenizer::hub::download_tokenizer_from_hf;
+    use sgl_model_gateway::tokenizer::hub::download_tokenizer_from_hf;
 
     // Test 4: Qwen3-VL has both tokenizer_config.json template and chat_template.json
     // Should prioritize chat_template.json
@@ -508,7 +508,7 @@ async fn test_qwen3_vl_json_template_priority() {
 
 #[tokio::test]
 async fn test_llava_separate_jinja_template() {
-    use sglang_router_rs::tokenizer::hub::download_tokenizer_from_hf;
+    use sgl_model_gateway::tokenizer::hub::download_tokenizer_from_hf;
 
     // Test 5: llava has chat_template.jinja as a separate file, not in tokenizer_config.json
     match download_tokenizer_from_hf("llava-hf/llava-1.5-7b-hf").await {
diff --git a/sgl-router/tests/tool_parser_deepseek.rs b/sgl-router/tests/tool_parser_deepseek.rs
index d3db93145..c47082895 100644
--- a/sgl-router/tests/tool_parser_deepseek.rs
+++ b/sgl-router/tests/tool_parser_deepseek.rs
@@ -1,6 +1,6 @@
 //! DeepSeek V3 Parser Integration Tests
 
-use sglang_router_rs::tool_parser::{DeepSeekParser, ToolParser};
+use sgl_model_gateway::tool_parser::{DeepSeekParser, ToolParser};
 
 mod common;
 use common::create_test_tools;
diff --git a/sgl-router/tests/tool_parser_edge_cases.rs b/sgl-router/tests/tool_parser_edge_cases.rs
index 2f11689a1..6fc4f6bcb 100644
--- a/sgl-router/tests/tool_parser_edge_cases.rs
+++ b/sgl-router/tests/tool_parser_edge_cases.rs
@@ -2,7 +2,7 @@
 //!
 //! Tests for malformed input, edge cases, and error recovery
 
-use sglang_router_rs::tool_parser::{
+use sgl_model_gateway::tool_parser::{
     JsonParser, MistralParser, PythonicParser, QwenParser, ToolParser,
 };
 
diff --git a/sgl-router/tests/tool_parser_fallback.rs b/sgl-router/tests/tool_parser_fallback.rs
index 16f185325..96b71bfe0 100644
--- a/sgl-router/tests/tool_parser_fallback.rs
+++ b/sgl-router/tests/tool_parser_fallback.rs
@@ -3,7 +3,7 @@
 //! When tool call parsing fails, the original text should be preserved as normal text
 //! rather than being lost. This ensures graceful degradation.
 
-use sglang_router_rs::tool_parser::{
+use sgl_model_gateway::tool_parser::{
     DeepSeekParser, JsonParser, LlamaParser, MistralParser, QwenParser, ToolParser,
 };
 
diff --git a/sgl-router/tests/tool_parser_glm4_moe.rs b/sgl-router/tests/tool_parser_glm4_moe.rs
index 86d161c9e..1e001a9f6 100644
--- a/sgl-router/tests/tool_parser_glm4_moe.rs
+++ b/sgl-router/tests/tool_parser_glm4_moe.rs
@@ -1,6 +1,6 @@
 //! GLM-4 MoE Parser Integration Tests
 
-use sglang_router_rs::tool_parser::{Glm4MoeParser, ToolParser};
+use sgl_model_gateway::tool_parser::{Glm4MoeParser, ToolParser};
 
 mod common;
 use common::create_test_tools;
diff --git a/sgl-router/tests/tool_parser_json.rs b/sgl-router/tests/tool_parser_json.rs
index 8e44d8d1e..fd3ca8f03 100644
--- a/sgl-router/tests/tool_parser_json.rs
+++ b/sgl-router/tests/tool_parser_json.rs
@@ -3,7 +3,7 @@
 //! Tests for the JSON parser which handles OpenAI, Claude, and generic JSON formats
 
 use serde_json::json;
-use sglang_router_rs::tool_parser::{JsonParser, ToolParser};
+use sgl_model_gateway::tool_parser::{JsonParser, ToolParser};
 
 mod common;
 use common::{create_test_tools, streaming_helpers::*};
@@ -166,7 +166,7 @@ async fn test_json_format_detection() {
 // Streaming tests for JSON array format
 #[tokio::test]
 async fn test_json_array_streaming_required_mode() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test that simulates the exact streaming pattern from required mode
     let mut parser = JsonParser::new();
@@ -174,7 +174,7 @@ async fn test_json_array_streaming_required_mode() {
     // Define test tools
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: serde_json::json!({}),
@@ -240,7 +240,7 @@ async fn test_json_array_streaming_required_mode() {
 
 #[tokio::test]
 async fn test_json_array_multiple_tools_streaming() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test with multiple tools in array
     let mut parser = JsonParser::new();
@@ -248,7 +248,7 @@ async fn test_json_array_multiple_tools_streaming() {
     let tools = vec![
         Tool {
             tool_type: "function".to_string(),
-            function: sglang_router_rs::protocols::common::Function {
+            function: sgl_model_gateway::protocols::common::Function {
                 name: "get_weather".to_string(),
                 description: Some("Get weather".to_string()),
                 parameters: serde_json::json!({}),
@@ -257,7 +257,7 @@ async fn test_json_array_multiple_tools_streaming() {
         },
         Tool {
             tool_type: "function".to_string(),
-            function: sglang_router_rs::protocols::common::Function {
+            function: sgl_model_gateway::protocols::common::Function {
                 name: "get_news".to_string(),
                 description: Some("Get news".to_string()),
                 parameters: serde_json::json!({}),
@@ -305,14 +305,14 @@ async fn test_json_array_multiple_tools_streaming() {
 
 #[tokio::test]
 async fn test_json_array_closing_bracket_separate_chunk() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test case where the closing ] comes as a separate chunk
     let mut parser = JsonParser::new();
 
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: json!({}),
@@ -366,14 +366,14 @@ async fn test_json_array_closing_bracket_separate_chunk() {
 
 #[tokio::test]
 async fn test_json_single_object_with_trailing_text() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test single object format (no array) with trailing text
     let mut parser = JsonParser::new();
 
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: serde_json::json!({}),
@@ -420,14 +420,14 @@ async fn test_json_single_object_with_trailing_text() {
 
 #[tokio::test]
 async fn test_json_single_object_with_bracket_in_text() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test that ] in normal text is NOT stripped for single object format
     let mut parser = JsonParser::new();
 
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: serde_json::json!({}),
@@ -472,14 +472,14 @@ async fn test_json_single_object_with_bracket_in_text() {
 
 #[tokio::test]
 async fn test_json_array_bracket_in_text_after_tools() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test that ] in normal text AFTER array tools is preserved
     let mut parser = JsonParser::new();
 
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: serde_json::json!({}),
diff --git a/sgl-router/tests/tool_parser_kimik2.rs b/sgl-router/tests/tool_parser_kimik2.rs
index f7f0a6c96..f7e8462a2 100644
--- a/sgl-router/tests/tool_parser_kimik2.rs
+++ b/sgl-router/tests/tool_parser_kimik2.rs
@@ -1,6 +1,6 @@
 //! Kimi K2 Parser Integration Tests
 
-use sglang_router_rs::tool_parser::{KimiK2Parser, ToolParser};
+use sgl_model_gateway::tool_parser::{KimiK2Parser, ToolParser};
 
 mod common;
 use common::create_test_tools;
diff --git a/sgl-router/tests/tool_parser_llama.rs b/sgl-router/tests/tool_parser_llama.rs
index a29912178..b07ff4acf 100644
--- a/sgl-router/tests/tool_parser_llama.rs
+++ b/sgl-router/tests/tool_parser_llama.rs
@@ -2,7 +2,7 @@
 //!
 //! Tests for the Llama parser which handles <|python_tag|> format and plain JSON
 
-use sglang_router_rs::tool_parser::{LlamaParser, ToolParser};
+use sgl_model_gateway::tool_parser::{LlamaParser, ToolParser};
 
 mod common;
 use common::{create_test_tools, streaming_helpers::*};
diff --git a/sgl-router/tests/tool_parser_minimax_m2.rs b/sgl-router/tests/tool_parser_minimax_m2.rs
index a6b296ec5..d47342ee0 100644
--- a/sgl-router/tests/tool_parser_minimax_m2.rs
+++ b/sgl-router/tests/tool_parser_minimax_m2.rs
@@ -1,6 +1,6 @@
 //! MiniMax M2 Parser Integration Tests
 
-use sglang_router_rs::tool_parser::{MinimaxM2Parser, ToolParser};
+use sgl_model_gateway::tool_parser::{MinimaxM2Parser, ToolParser};
 
 mod common;
 use common::create_test_tools;
diff --git a/sgl-router/tests/tool_parser_mistral.rs b/sgl-router/tests/tool_parser_mistral.rs
index 42b75a0cf..321aa6686 100644
--- a/sgl-router/tests/tool_parser_mistral.rs
+++ b/sgl-router/tests/tool_parser_mistral.rs
@@ -3,7 +3,7 @@
 //! Tests for the Mistral parser which handles [TOOL_CALLS] format
 
 use serde_json::json;
-use sglang_router_rs::tool_parser::{MistralParser, ToolParser};
+use sgl_model_gateway::tool_parser::{MistralParser, ToolParser};
 
 #[tokio::test]
 async fn test_mistral_single_tool() {
@@ -158,14 +158,14 @@ Let me execute these searches for you."#;
 
 #[tokio::test]
 async fn test_mistral_streaming_closing_bracket() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test that closing ] is stripped for Mistral array format
     let mut parser = MistralParser::new();
 
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: json!({}),
@@ -218,14 +218,14 @@ async fn test_mistral_streaming_closing_bracket() {
 
 #[tokio::test]
 async fn test_mistral_streaming_bracket_in_text_after_tools() {
-    use sglang_router_rs::protocols::common::Tool;
+    use sgl_model_gateway::protocols::common::Tool;
 
     // Test that ] in normal text AFTER tool calls is preserved
     let mut parser = MistralParser::new();
 
     let tools = vec![Tool {
         tool_type: "function".to_string(),
-        function: sglang_router_rs::protocols::common::Function {
+        function: sgl_model_gateway::protocols::common::Function {
             name: "get_weather".to_string(),
             description: Some("Get weather".to_string()),
             parameters: json!({}),
diff --git a/sgl-router/tests/tool_parser_mixed_edge_cases.rs b/sgl-router/tests/tool_parser_mixed_edge_cases.rs
index d722ee1a2..db3898df2 100644
--- a/sgl-router/tests/tool_parser_mixed_edge_cases.rs
+++ b/sgl-router/tests/tool_parser_mixed_edge_cases.rs
@@ -3,7 +3,7 @@
 //! Tests for edge cases across parsers and mixed format scenarios
 
 use serde_json::json;
-use sglang_router_rs::tool_parser::{
+use sgl_model_gateway::tool_parser::{
     JsonParser, LlamaParser, MistralParser, PythonicParser, QwenParser, ToolParser,
 };
 
diff --git a/sgl-router/tests/tool_parser_partial_json.rs b/sgl-router/tests/tool_parser_partial_json.rs
index 36d493651..e3c28a237 100644
--- a/sgl-router/tests/tool_parser_partial_json.rs
+++ b/sgl-router/tests/tool_parser_partial_json.rs
@@ -2,7 +2,7 @@
 //!
 //! Tests for the partial JSON parser with allow_partial_strings flag behavior
 
-use sglang_router_rs::tool_parser::partial_json::PartialJson;
+use sgl_model_gateway::tool_parser::partial_json::PartialJson;
 
 #[test]
 fn test_partial_string_flag_disallows_incomplete_strings() {
diff --git a/sgl-router/tests/tool_parser_pythonic.rs b/sgl-router/tests/tool_parser_pythonic.rs
index 1215bbe4c..a5c0b46de 100644
--- a/sgl-router/tests/tool_parser_pythonic.rs
+++ b/sgl-router/tests/tool_parser_pythonic.rs
@@ -3,7 +3,7 @@
 //! Tests for the Pythonic parser which handles Python function call syntax
 
 use serde_json::json;
-use sglang_router_rs::tool_parser::{PythonicParser, ToolParser};
+use sgl_model_gateway::tool_parser::{PythonicParser, ToolParser};
 
 mod common;
 use common::create_test_tools;
diff --git a/sgl-router/tests/tool_parser_qwen.rs b/sgl-router/tests/tool_parser_qwen.rs
index 01fee8fbf..c26164d59 100644
--- a/sgl-router/tests/tool_parser_qwen.rs
+++ b/sgl-router/tests/tool_parser_qwen.rs
@@ -3,7 +3,7 @@
 //! Tests for the Qwen parser which handles <tool_call>...</tool_call> format
 
 use serde_json::json;
-use sglang_router_rs::tool_parser::{QwenParser, ToolParser};
+use sgl_model_gateway::tool_parser::{QwenParser, ToolParser};
 
 mod common;
 use common::{create_test_tools, streaming_helpers::*};
diff --git a/sgl-router/tests/tool_parser_step3.rs b/sgl-router/tests/tool_parser_step3.rs
index 85cbacfae..03913e661 100644
--- a/sgl-router/tests/tool_parser_step3.rs
+++ b/sgl-router/tests/tool_parser_step3.rs
@@ -1,6 +1,6 @@
 //! Step3 Parser Integration Tests
 
-use sglang_router_rs::tool_parser::{Step3Parser, ToolParser};
+use sgl_model_gateway::tool_parser::{Step3Parser, ToolParser};
 
 mod common;
 use common::create_test_tools;
diff --git a/sgl-router/tests/workflow_test.rs b/sgl-router/tests/workflow_test.rs
index 6b2f58ee2..be36030c3 100644
--- a/sgl-router/tests/workflow_test.rs
+++ b/sgl-router/tests/workflow_test.rs
@@ -8,7 +8,7 @@ use std::{
     time::Duration,
 };
 
-use sglang_router_rs::core::workflow::*;
+use sgl_model_gateway::core::workflow::*;
 use tokio::time::sleep;
 
 // Test step that counts invocations