[router] disable rate limiter by default (#11435)

This commit is contained in:
Simo Lin
2025-10-10 20:43:07 -04:00
committed by GitHub
parent b36afed4a7
commit 2eeb27515a
7 changed files with 69 additions and 40 deletions

View File

@@ -65,7 +65,7 @@ struct Router {
decode_urls: Option<Vec<String>>,
prefill_policy: Option<PolicyType>,
decode_policy: Option<PolicyType>,
max_concurrent_requests: usize,
max_concurrent_requests: i32,
cors_allowed_origins: Vec<String>,
retry_max_retries: u32,
retry_initial_backoff_ms: u64,
@@ -86,7 +86,7 @@ struct Router {
enable_igw: bool,
queue_size: usize,
queue_timeout_secs: u64,
rate_limit_tokens_per_second: Option<usize>,
rate_limit_tokens_per_second: Option<i32>,
connection_mode: config::ConnectionMode,
model_path: Option<String>,
tokenizer_path: Option<String>,
@@ -260,7 +260,7 @@ impl Router {
decode_urls = None,
prefill_policy = None,
decode_policy = None,
max_concurrent_requests = 256,
max_concurrent_requests = -1,
cors_allowed_origins = vec![],
retry_max_retries = 5,
retry_initial_backoff_ms = 50,
@@ -321,7 +321,7 @@ impl Router {
decode_urls: Option<Vec<String>>,
prefill_policy: Option<PolicyType>,
decode_policy: Option<PolicyType>,
max_concurrent_requests: usize,
max_concurrent_requests: i32,
cors_allowed_origins: Vec<String>,
retry_max_retries: u32,
retry_initial_backoff_ms: u64,
@@ -342,7 +342,7 @@ impl Router {
enable_igw: bool,
queue_size: usize,
queue_timeout_secs: u64,
rate_limit_tokens_per_second: Option<usize>,
rate_limit_tokens_per_second: Option<i32>,
model_path: Option<String>,
tokenizer_path: Option<String>,
reasoning_parser: Option<String>,