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

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 11:33:35 +00:00
committed by GitHub
co-authored by TJian Cyrus Leung
parent 6eaf1e5c52
commit 2bb0e1a799
21 changed files with 174 additions and 99 deletions
+4 -5
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,
+6 -7
View File
@@ -4,10 +4,9 @@ import pytest
import ray
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 = "meta-llama/Llama-2-7b-hf"
@@ -82,7 +81,7 @@ def v1(run_with_both_engines_lora):
# V1 Test: Failing due to numerics on V1.
@pytest.mark.skip_v1
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_llama_lora(sql_lora_files):
llm = vllm.LLM(MODEL_PATH,
@@ -97,7 +96,7 @@ def test_llama_lora(sql_lora_files):
# Skipping for v1 as v1 doesn't have a good way to expose the num_gpu_blocks
# used by the engine yet.
@pytest.mark.skip_v1
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_llama_lora_warmup(sql_lora_files):
"""Test that the LLM initialization works with a warmup LORA path and
is more conservative"""
@@ -128,7 +127,7 @@ def test_llama_lora_warmup(sql_lora_files):
# V1 Test: Failing due to numerics on V1.
@pytest.mark.skip_v1
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_llama_lora_tp4(sql_lora_files):
llm = vllm.LLM(
@@ -143,7 +142,7 @@ def test_llama_lora_tp4(sql_lora_files):
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_llama_lora_tp4_fully_sharded_loras(sql_lora_files):
llm = vllm.LLM(
@@ -159,7 +158,7 @@ def test_llama_lora_tp4_fully_sharded_loras(sql_lora_files):
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_llama_lora_tp4_fully_sharded_enable_bias(sql_lora_files):
llm = vllm.LLM(
+5 -4
View File
@@ -3,11 +3,12 @@
import pytest
import vllm
from tests.utils import fork_new_process_for_each_test
from vllm.assets.image import ImageAsset
from vllm.lora.request import LoRARequest
from vllm.platforms import current_platform
from ..utils import create_new_process_for_each_test
MODEL_PATH = "openbmb/MiniCPM-Llama3-V-2_5"
PROMPT_TEMPLATE = (
@@ -57,7 +58,7 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
@pytest.mark.xfail(
current_platform.is_rocm(),
reason="MiniCPM-V dependency xformers incompatible with ROCm")
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_minicpmv_lora(minicpmv_lora_files):
llm = vllm.LLM(
MODEL_PATH,
@@ -80,7 +81,7 @@ def test_minicpmv_lora(minicpmv_lora_files):
@pytest.mark.xfail(
current_platform.is_rocm(),
reason="MiniCPM-V dependency xformers incompatible with ROCm")
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_minicpmv_tp4_wo_fully_sharded_loras(minicpmv_lora_files):
llm = vllm.LLM(
MODEL_PATH,
@@ -101,7 +102,7 @@ def test_minicpmv_tp4_wo_fully_sharded_loras(minicpmv_lora_files):
@pytest.mark.xfail(
current_platform.is_rocm(),
reason="MiniCPM-V dependency xformers incompatible with ROCm")
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_minicpmv_tp4_fully_sharded_loras(minicpmv_lora_files):
llm = vllm.LLM(
MODEL_PATH,
+4 -5
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 = "ArthurZ/ilama-3.2-1B"
@@ -56,7 +55,7 @@ def v1(run_with_both_engines_lora):
@pytest.mark.skip_v1
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_ilama_lora(ilama_lora_files):
llm = vllm.LLM(MODEL_PATH,
max_model_len=1024,
@@ -77,7 +76,7 @@ def test_ilama_lora(ilama_lora_files):
@pytest.mark.skip_v1
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_ilama_lora_tp4(ilama_lora_files):
llm = vllm.LLM(MODEL_PATH,
max_model_len=1024,
@@ -99,7 +98,7 @@ def test_ilama_lora_tp4(ilama_lora_files):
@pytest.mark.skip_v1
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_ilama_lora_tp4_fully_sharded_loras(ilama_lora_files):
llm = vllm.LLM(MODEL_PATH,
max_model_len=1024,