mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 04:14:52 +00:00
Cargo fmt
This commit is contained in:
parent
d99f281050
commit
269792094b
@ -162,7 +162,6 @@ struct Args {
|
||||
#[clap(long, env)]
|
||||
speculate: Option<usize>,
|
||||
|
||||
|
||||
/// The dtype to be forced upon the model. This option cannot be used with `--quantize`.
|
||||
#[clap(long, env, value_enum)]
|
||||
dtype: Option<Dtype>,
|
||||
|
@ -10,7 +10,7 @@ pub use pb::generate::v1::HealthResponse;
|
||||
pub use pb::generate::v1::InfoResponse as ShardInfo;
|
||||
pub use pb::generate::v1::{
|
||||
Batch, CachedBatch, FinishReason, GeneratedText, Generation, NextTokenChooserParameters,
|
||||
Tokens, Request, StoppingCriteriaParameters,
|
||||
Request, StoppingCriteriaParameters, Tokens,
|
||||
};
|
||||
pub use sharded_client::ShardedClient;
|
||||
use thiserror::Error;
|
||||
|
@ -9,7 +9,7 @@ use std::sync::{
|
||||
Arc,
|
||||
};
|
||||
use text_generation_client::{
|
||||
Batch, CachedBatch, ClientError, GeneratedText, Generation, Tokens, ShardedClient,
|
||||
Batch, CachedBatch, ClientError, GeneratedText, Generation, ShardedClient, Tokens,
|
||||
};
|
||||
use thiserror::Error;
|
||||
use tokio::sync::mpsc::error::SendError;
|
||||
@ -525,7 +525,9 @@ fn send_responses(
|
||||
|
||||
// Create last Token
|
||||
let tokens: Vec<Token> = if let Some(tokens_) = generation.tokens {
|
||||
tokens_.ids.into_iter()
|
||||
tokens_
|
||||
.ids
|
||||
.into_iter()
|
||||
.zip(tokens_.logprobs.into_iter())
|
||||
.zip(tokens_.texts.into_iter())
|
||||
.zip(tokens_.is_special.into_iter())
|
||||
@ -534,7 +536,8 @@ fn send_responses(
|
||||
text,
|
||||
logprob,
|
||||
special,
|
||||
}).collect()
|
||||
})
|
||||
.collect()
|
||||
} else {
|
||||
vec![]
|
||||
};
|
||||
|
Loading…
Reference in New Issue
Block a user