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 12, 18:30 UTC
[Misc] remove useless v1 env (#29164)
Signed-off-by: David Chen <530634352@qq.com>
WeiQing Chen committed
Nov 21, 2025 at 17:41 UTC
b34129bf8e5412e4094b89aba5246605c280a5fd
1 file changed
-2
tests/v1/e2e/test_lora_with_spec_decode.py
-2
@@ -61,8 +61,6 @@ def test_batch_inference_correctness(
61
model_setup: (method, model_name, spec_model_name, lora_path, tp_size)
62
"""
63
with monkeypatch.context() as m:
64
- m.setenv("VLLM_USE_V1", "1")
65
-
64
# Disable randomness
65
m.setenv("CUBLAS_WORKSPACE_CONFIG", ":4096:8")
66
torch.manual_seed(SEED)