apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Others] clean code (#5133)

Browse Source
This commit is contained in:
周周周
2025-11-20 18:44:08 +08:00
committed by GitHub
parent 7ac25935c7
commit 385fe6dade
3 changed files with 51 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/entrypoints/openai/test_run_batch.py
View File

@@ -172,7 +172,7 @@ class TestEngineInitialization(unittest.TestCase):
mock_args = Mock()
mock_args.model = "test-model"
mock_args.tokenizer = "test-tokenizer"
mock_args.max_model_len = 1000
mock_args.max_model_len = 1024
mock_args.tensor_parallel_size = 1
mock_args.engine_worker_queue_port = [8000]
mock_args.local_data_parallel_id = 0
@@ -202,7 +202,7 @@ class TestEngineInitialization(unittest.TestCase):
def test_create_serving_handlers(self, mock_chat_handler, mock_model_handler):
"""测试创建服务处理器"""
mock_args = Mock()
mock_args.max_model_len = 1000
mock_args.max_model_len = 1024
mock_args.ips = "127.0.0.1"
mock_args.max_waiting_time = 60
mock_args.enable_mm_output = False
@@ -1286,7 +1286,7 @@ class TestFastDeployBatch(unittest.TestCase):
"--quantization",
"wint4",
"--max-model-len",
"4192",
"5120",
"--max-num-seqs",
"64",
"--load-choices",