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
[CI/Build] Reduce the number of redundant cases to test for LoRA (#24276)
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Zhuohan Li committed
Sep 4, 2025 at 14:58 UTC
886ccbe5bae5ac3562f2b73c7770bba73d2ea34e
1 file changed
+2
-2
tests/lora/test_layers.py
+2
-2
@@ -60,9 +60,9 @@ DEVICES = ([
60
# prefill stage(True) or decode stage(False)
61
STAGES = [True, False]
62
63
-NUM_RANDOM_SEEDS = 6
63
+NUM_RANDOM_SEEDS = 2
64
65
-VOCAB_PARALLEL_EMBEDDING_TEST_NUM_RANDOM_SEEDS = 128
65
+VOCAB_PARALLEL_EMBEDDING_TEST_NUM_RANDOM_SEEDS = 2
66
67
68
@pytest.fixture(autouse=True)