huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Obey max batch size

Browse Source
This commit is contained in:
Nick Hill 2023-01-16 21:59:37 -08:00
parent fcc2c5fcbf
commit dff8f7cde7
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
router/src/batcher.rs
View File

@ -128,7 +128,7 @@ async fn batching_task(
// Try to get a new batch // Try to get a new batch
if let Some((new_request_ids, new_batch)) = if let Some((new_request_ids, new_batch)) =
db.next_batch(min_size, max_batch_size) db.next_batch(min_size, max_batch_size - batch_size as usize)
{ {
// Generate one token for this new batch to have the attention past in cache // Generate one token for this new batch to have the attention past in cache
let new_cached_batch = let new_cached_batch =