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
Added test_top_k_per_row to test-pipeline.yaml. (#26569)
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Daniel Cámpora committed
Oct 10, 2025 at 16:48 UTC
0e67102d93ac06f5a00acaaaf59ed45ebe98c29d
2 files changed
+2
-2
.buildkite/test-pipeline.yaml
+2
-1
@@ -431,8 +431,9 @@ steps:
431
source_file_dependencies:
432
- csrc/
433
- tests/kernels/core
434
+ - tests/kernels/test_top_k_per_row.py
435
commands:
435
- - pytest -v -s kernels/core
436
+ - pytest -v -s kernels/core kernels/test_top_k_per_row.py
437
438
- label: Kernels Attention Test %N # 23min
439
timeout_in_minutes: 35
tests/kernels/test_top_k_per_row.py
-1
@@ -125,7 +125,6 @@ def test_top_k_per_row(
125
indices,
126
values,
127
num_rows,
128
- top_k,
128
logits.stride(0),
129
logits.stride(1),
130
)