diff --git a/router/client/src/client.rs b/router/client/src/client.rs index 5c6ee38d..f8f5df95 100644 --- a/router/client/src/client.rs +++ b/router/client/src/client.rs @@ -128,7 +128,7 @@ impl Client { watermark: true, }), stopping_parameters: Some(StoppingCriteriaParameters { - max_new_tokens: max_total_tokens-truncate, + max_new_tokens: max_total_tokens - truncate, stop_sequences: vec![], ignore_eos_token: true, }), diff --git a/router/client/src/sharded_client.rs b/router/client/src/sharded_client.rs index ef974d56..b4bdcd42 100644 --- a/router/client/src/sharded_client.rs +++ b/router/client/src/sharded_client.rs @@ -100,7 +100,9 @@ impl ShardedClient { let futures: Vec<_> = self .clients .iter_mut() - .map(|client| Box::pin(client.warmup(max_input_length, max_prefill_tokens, max_total_tokens))) + .map(|client| { + Box::pin(client.warmup(max_input_length, max_prefill_tokens, max_total_tokens)) + }) .collect(); // Take the minimum value let results = join_all(futures) diff --git a/router/src/validation.rs b/router/src/validation.rs index d0ea137d..37465272 100644 --- a/router/src/validation.rs +++ b/router/src/validation.rs @@ -122,7 +122,7 @@ impl Validation { if let Some(truncate) = truncate { self.max_total_tokens.saturating_sub(truncate) as u32 } else { - return Err(ValidationError::UnsetMaxNewTokens) + return Err(ValidationError::UnsetMaxNewTokens); } }; let input_length = truncate.unwrap_or(self.max_input_length);