huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update router/src/infer.rs

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-30 11:25:37 +02:00
parent 13caf958eb
commit be87c840b8
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/infer.rs
View File

@ -76,7 +76,7 @@ impl Infer {
} else {
false
};
let block_size = if flashdecoding { 256 } else { 32 };
let block_size = if flashdecoding { 256 } else { 16 };
let block_size = std::env::var("BLOCK_SIZE")
.map(|b| b.parse().unwrap_or(block_size))
.unwrap_or(block_size);