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

benchmark: fix prefill throughput

Browse Source
This commit is contained in:
Daniël de Kok 2024-11-12 09:17:37 +00:00
parent a785000842
commit d6c8426b91
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
benchmark/src/generation.rs
View File

@ -180,7 +180,7 @@ async fn prefill(
let latency = start_time.elapsed();
// Compute throughput from latency and batch size
let throughput = batch_size as f64 / latency.as_secs_f64();
let throughput = (batch_size * sequence_length) as f64 / latency.as_secs_f64();
// Decode batch cannot be empty
let decode_batch = decode_batch.expect("decode_batch is None. This is a bug.");