biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix][ROCm] running new process using spawn method for rocm in tests. (#14810)

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
vllmellm
2025-03-17 19:33:35 +08:00
committed by GitHub
parent 6eaf1e5c52
commit 2bb0e1a799
21 changed files with 174 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/lora/test_chatglm3_tp.py
View File

@@ -3,10 +3,9 @@
import pytest
import vllm
from tests.utils import fork_new_process_for_each_test
from vllm.lora.request import LoRARequest
from ..utils import multi_gpu_test
from ..utils import create_new_process_for_each_test, multi_gpu_test
MODEL_PATH = "THUDM/chatglm3-6b"
@@ -55,7 +54,7 @@ def v1(run_with_both_engines_lora):
pass
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_chatglm3_lora(chatglm3_lora_files):
llm = vllm.LLM(MODEL_PATH,
max_model_len=1024,
@@ -75,7 +74,7 @@ def test_chatglm3_lora(chatglm3_lora_files):
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_chatglm3_lora_tp4(chatglm3_lora_files):
llm = vllm.LLM(MODEL_PATH,
max_model_len=1024,
@@ -96,7 +95,7 @@ def test_chatglm3_lora_tp4(chatglm3_lora_files):
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_chatglm3_lora_tp4_fully_sharded_loras(chatglm3_lora_files):
llm = vllm.LLM(MODEL_PATH,
max_model_len=1024,