huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 08:22:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

misc(backend): decrease log verbosity in callback

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-11-04 23:24:50 +01:00
parent 1149186794
commit 52208f5b78
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
backends/llamacpp/src/backend.rs
View File

@ -17,7 +17,7 @@ use tokenizers::Tokenizer;
use tokio::sync::mpsc::{unbounded_channel, UnboundedSender}; use tokio::sync::mpsc::{unbounded_channel, UnboundedSender};
use tokio::time::Instant; use tokio::time::Instant;
use tokio_stream::wrappers::UnboundedReceiverStream; use tokio_stream::wrappers::UnboundedReceiverStream;
use tracing::{error, info}; use tracing::{debug, error, info};
type InferResult = Result<InferStreamResponse, InferError>; type InferResult = Result<InferStreamResponse, InferError>;
@ -113,7 +113,7 @@ fn llama_generate_callback(
is_final: bool, is_final: bool,
n_generated_tokens: usize, n_generated_tokens: usize,
) -> bool { ) -> bool {
info!("Generated token: {new_token_id} -> logits={new_token_logit}, is_final={is_final} ({n_generated_tokens})"); debug!("Generated token: {new_token_id} -> logits={new_token_logit}, is_final={is_final} ({n_generated_tokens})");
let ctx = unsafe { &mut *ctx }; let ctx = unsafe { &mut *ctx };