A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Bug] fix import and unit test (#25558)
Signed-off-by: Jonas M. Kübler <44084297+jmkuebler@users.noreply.github.com>
Jonas M. Kübler committed
Sep 24, 2025 at 12:17 UTC
58c360d9be8c3963bf5cdf82a275570e759adef1
1 file changed
+1
-1
tests/v1/attention/test_attention_splitting.py
+1
-1
@@ -11,7 +11,7 @@ from vllm.v1.attention.backends.utils import (UBatchSlice,
11
slice_query_start_locs,
12
split_attn_metadata,
13
split_decodes_and_prefills)
14
-from vllm.v1.worker.ubatch_utils import create_ubatch_slices
14
+from vllm.v1.worker.ubatch_splitting import create_ubatch_slices
15
16
17
@pytest.fixture