apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-07 09:31:35 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix (#3676)

Browse Source 
* fix

* update
This commit is contained in:
bukejiyu
2025-08-28 17:06:32 +08:00
committed by GitHub
parent 98c217b428
commit 73cf6096da
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/conftest.py
View File

@@ -15,6 +15,7 @@ import os
import signal import signal
import socket import socket
import subprocess import subprocess
import time
from typing import Any, Union from typing import Any, Union
import pytest import pytest
@@ -70,6 +71,7 @@ class FDRunner:
if "engine_worker_queue_port" in kwargs: if "engine_worker_queue_port" in kwargs:
ports_to_clean.append(kwargs["engine_worker_queue_port"]) ports_to_clean.append(kwargs["engine_worker_queue_port"])
clean_ports(ports_to_clean) clean_ports(ports_to_clean)
time.sleep(5)
self.llm = LLM( self.llm = LLM(
model=model_name_or_path, model=model_name_or_path,
tensor_parallel_size=tensor_parallel_size, tensor_parallel_size=tensor_parallel_size,

2
tests/model_loader/test_common_model.py
View File

@@ -166,7 +166,7 @@ model_param_map = {
], ],
}, },
"Qwen2-7B-Instruct": { "Qwen2-7B-Instruct": {
"quantizations": ["None", "wint8"], "quantizations": ["wint4"],
}, },
"Qwen3-30B-A3B": { "Qwen3-30B-A3B": {
"tensor_parallel_size": 2, "tensor_parallel_size": 2,