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/lora/test_llama_tp.py
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(