xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 04:34:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1] reduce block size for tree attention correctness test to fix 'ou… (#22207)

Browse Source 
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
This commit is contained in:
Giancarlo Delfin 2025-08-04 19:11:06 -07:00 committed by GitHub
parent 7175817637
commit 5ea71ff46f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/v1/spec_decode/test_tree_attention.py
View File

@ -155,7 +155,7 @@ def test_tree_attn_correctness() -> None:
dim_per_head = 128 dim_per_head = 128
num_kv_heads = 2 num_kv_heads = 2
block_size = 128 block_size = 32
max_sequence_length = 8192 max_sequence_length = 8192
randomize_blocks = True randomize_blocks = True
for batch_size in [1, 16, 32]: for batch_size in [1, 16, 32]: