biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[TPU] update TPU benchmark threshold (#25713)

Browse Source 
Signed-off-by: Johnny Yang <johnnyyang@google.com>
This commit is contained in:
Johnny Yang
2025-10-07 13:53:09 -07:00
committed by GitHub
parent 3d1f67616d
commit 59012df99b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/scripts/tpu/quantized_v6e_1.env
View File

@@ -9,6 +9,6 @@ MAX_NUM_BATCHED_TOKENS=1024
TENSOR_PARALLEL_SIZE=1
MAX_MODEL_LEN=2048
DOWNLOAD_DIR=/mnt/disks/persist
EXPECTED_THROUGHPUT=10.0
EXPECTED_THROUGHPUT=8.7
INPUT_LEN=1800
OUTPUT_LEN=128