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

13
tests/quantization/test_bitsandbytes.py
View File

@@ -10,7 +10,8 @@ import pytest
import torch
from tests.quantization.utils import is_quant_method_supported
from tests.utils import compare_two_settings, fork_new_process_for_each_test
from ..utils import compare_two_settings, create_new_process_for_each_test
models_4bit_to_test = [
("facebook/opt-125m", "quantize opt model inflight"),
@@ -32,7 +33,7 @@ models_pre_quant_8bit_to_test = [
@pytest.mark.skipif(not is_quant_method_supported("bitsandbytes"),
reason='bitsandbytes is not supported on this GPU type.')
@pytest.mark.parametrize("model_name, description", models_4bit_to_test)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_load_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
model_name, description) -> None:
@@ -45,7 +46,7 @@ def test_load_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
reason='bitsandbytes is not supported on this GPU type.')
@pytest.mark.parametrize("model_name, description",
models_pre_qaunt_4bit_to_test)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_load_pre_quant_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
model_name, description) -> None:
@@ -57,7 +58,7 @@ def test_load_pre_quant_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
reason='bitsandbytes is not supported on this GPU type.')
@pytest.mark.parametrize("model_name, description",
models_pre_quant_8bit_to_test)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_load_8bit_bnb_model(hf_runner, vllm_runner, example_prompts,
model_name, description) -> None:
@@ -70,7 +71,7 @@ def test_load_8bit_bnb_model(hf_runner, vllm_runner, example_prompts,
@pytest.mark.skipif(not is_quant_method_supported("bitsandbytes"),
reason='bitsandbytes is not supported on this GPU type.')
@pytest.mark.parametrize("model_name, description", models_4bit_to_test)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_load_tp_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
model_name, description) -> None:
@@ -88,7 +89,7 @@ def test_load_tp_4bit_bnb_model(hf_runner, vllm_runner, example_prompts,
@pytest.mark.skipif(not is_quant_method_supported("bitsandbytes"),
reason='bitsandbytes is not supported on this GPU type.')
@pytest.mark.parametrize("model_name, description", models_4bit_to_test)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_load_pp_4bit_bnb_model(model_name, description) -> None:
common_args = [
"--disable-log-stats",