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

26
tests/spec_decode/e2e/test_multistep_correctness.py
View File

@@ -42,7 +42,7 @@ from transformers import AutoTokenizer
from vllm import SamplingParams
from ...utils import fork_new_process_for_each_test
from ...utils import create_new_process_for_each_test
from .conftest import (get_output_from_llm_generator,
run_equality_correctness_test)
@@ -82,7 +82,7 @@ from .conftest import (get_output_from_llm_generator,
@pytest.mark.parametrize("test_llm_kwargs", [{}])
@pytest.mark.parametrize("batch_size", [1, 32])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_with_detokenization(test_llm_generator,
batch_size: int):
"""Run generation with speculative decoding on a batch. Verify the engine
@@ -170,7 +170,7 @@ def test_spec_decode_e2e_with_detokenization(test_llm_generator,
])
@pytest.mark.parametrize("batch_size", [1])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_greedy_correctness_tiny_model_bs1(
vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int, output_len: int,
@@ -244,7 +244,7 @@ def test_spec_decode_e2e_greedy_correctness_tiny_model_bs1(
])
@pytest.mark.parametrize("batch_size", [64])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_greedy_correctness_tiny_model_large_bs(
vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int, output_len: int,
@@ -300,7 +300,7 @@ def test_spec_decode_e2e_greedy_correctness_tiny_model_large_bs(
])
@pytest.mark.parametrize("batch_size", [32])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_greedy_correctness_tiny_model_large_bs_diff_output_len(
vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int,
@@ -356,7 +356,7 @@ def test_spec_decode_e2e_greedy_correctness_tiny_model_large_bs_diff_output_len(
256,
])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_greedy_correctness_real_model_bs1(
vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int, output_len: int,
@@ -411,7 +411,7 @@ def test_spec_decode_e2e_greedy_correctness_real_model_bs1(
64,
])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_greedy_correctness_real_model_large_bs(
vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int, output_len: int,
@@ -469,7 +469,7 @@ def test_spec_decode_e2e_greedy_correctness_real_model_large_bs(
])
@pytest.mark.parametrize("batch_size", [4])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_e2e_greedy_correctness_with_preemption(
vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int, output_len: int,
@@ -534,7 +534,7 @@ def test_spec_decode_e2e_greedy_correctness_with_preemption(
32,
])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_spec_decode_different_block_size(vllm_runner, common_llm_kwargs,
per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs,
@@ -594,7 +594,7 @@ def test_spec_decode_different_block_size(vllm_runner, common_llm_kwargs,
64,
])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_skip_speculation(vllm_runner, common_llm_kwargs,
per_test_common_llm_kwargs, baseline_llm_kwargs,
test_llm_kwargs, batch_size: int, output_len: int,
@@ -644,7 +644,7 @@ def test_skip_speculation(vllm_runner, common_llm_kwargs,
@pytest.mark.parametrize("batch_size", [8])
@pytest.mark.parametrize("output_len", [10])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_disable_speculation(vllm_runner, common_llm_kwargs,
per_test_common_llm_kwargs, baseline_llm_kwargs,
test_llm_kwargs, batch_size: int, output_len: int,
@@ -697,7 +697,7 @@ def test_disable_speculation(vllm_runner, common_llm_kwargs,
32,
])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_many_k(vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs, batch_size: int,
output_len: int, seed: int):
@@ -752,7 +752,7 @@ def test_many_k(vllm_runner, common_llm_kwargs, per_test_common_llm_kwargs,
32,
])
@pytest.mark.parametrize("seed", [1])
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_typical_acceptance_sampling(vllm_runner, common_llm_kwargs,
per_test_common_llm_kwargs,
baseline_llm_kwargs, test_llm_kwargs,