huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Removing the logs.

Browse Source
This commit is contained in:
Nicolas Patry 2024-08-14 11:29:40 +02:00
parent 4fff77ebcb
commit 4a38185d78
No known key found for this signature in database
GPG Key ID: 64AF4752B2967863
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backends/v3/src/radix.rs
View File

@ -89,8 +89,6 @@ impl Allocator for RadixAllocator {
let prefix_len = blocks.len(); let prefix_len = blocks.len();
let suffix_len = tokens - prefix_len as u32; let suffix_len = tokens - prefix_len as u32;
tracing::info!("Prefix {prefix_len} - Suffix {suffix_len}");
match self.alloc_or_reclaim(suffix_len as usize) { match self.alloc_or_reclaim(suffix_len as usize) {
Some(suffix_blocks) => blocks.extend(suffix_blocks), Some(suffix_blocks) => blocks.extend(suffix_blocks),
None => { None => {

2
server/text_generation_server/models/flash_causal_lm.py
View File

@ -1743,7 +1743,7 @@ class FlashCausalLM(Model):
left = 0 left = 0
if n_accepted_ids > 1: if n_accepted_ids > 1:
log_master(logger.info, f"Speculated ids {n_accepted_ids - 1}") log_master(logger.debug, f"Speculated ids {n_accepted_ids - 1}")
current_stopped = False current_stopped = False
for j in range(index, index + n_accepted_ids): for j in range(index, index + n_accepted_ids):