EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Lint]Style: Convert test/ to ruff format(Batch #1) (#6738)

Browse Source 
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| `tests/e2e/310p/multicard/test_vl_model_multicard.py` |
| `tests/e2e/310p/singlecard/test_vl_model_singlecard.py` |
| `tests/e2e/310p/test_utils.py` |
| `tests/e2e/conftest.py` |
| `tests/e2e/model_utils.py` |
| `tests/e2e/models/conftest.py` |
| `tests/e2e/models/test_lm_eval_correctness.py` |
| `tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py` |
| `tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py` |
| `tests/e2e/multicard/2-cards/test_data_parallel.py` |
| `tests/e2e/multicard/2-cards/test_disaggregated_encoder.py` |
| `tests/e2e/multicard/2-cards/test_expert_parallel.py` |
| `tests/e2e/multicard/2-cards/test_external_launcher.py` |
| `tests/e2e/multicard/2-cards/test_full_graph_mode.py` |
| `tests/e2e/multicard/2-cards/test_ilama_lora_tp2.py` |
| `tests/e2e/multicard/2-cards/test_offline_inference_distributed.py` |
| `tests/e2e/multicard/2-cards/test_offline_weight_load.py` |
| `tests/e2e/multicard/2-cards/test_pipeline_parallel.py` |
| `tests/e2e/multicard/2-cards/test_prefix_caching.py` |
| `tests/e2e/multicard/2-cards/test_quantization.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_moe.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_moe_routing_replay.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_performance.py` |
| `tests/e2e/multicard/2-cards/test_shared_expert_dp.py` |
| `tests/e2e/multicard/2-cards/test_single_request_aclgraph.py` |
| `tests/e2e/multicard/2-cards/test_sp_pass.py` |

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
9562912cea

Signed-off-by: MrZ20 <2609716663@qq.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
SILONG ZENG
2026-03-10 09:52:50 +08:00
committed by GitHub
parent 9216e1b050
commit 43df2cb2fc
27 changed files with 753 additions and 859 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tests/e2e/310p/multicard/test_vl_model_multicard.py
View File

@@ -15,28 +15,23 @@
# limitations under the License.
# This file is a part of the vllm-ascend project.
import sys
import os
import sys
# Add 310p directory to sys.path
current_dir = os.path.dirname(os.path.abspath(__file__))
parent_dir = os.path.dirname(current_dir) # 310p directory
sys.path.insert(0, parent_dir)
# ruff: noqa: E402
from test_utils import run_vl_model_test
def test_qwen3_vl_8b_tp2_fp16():
"""Qwen3-VL-8B dual-card FP16 test"""
run_vl_model_test(
model_name="Qwen/Qwen3-VL-8B-Instruct",
tensor_parallel_size=2,
max_tokens=5
)
run_vl_model_test(model_name="Qwen/Qwen3-VL-8B-Instruct", tensor_parallel_size=2, max_tokens=5)
def test_qwen3_vl_32b_tp1_fp16():
"""Qwen3-VL-32B 4-card FP16 test"""
run_vl_model_test(
model_name="Qwen/Qwen3-VL-32B-Instruct",
tensor_parallel_size=4,
max_tokens=5
)
run_vl_model_test(model_name="Qwen/Qwen3-VL-32B-Instruct", tensor_parallel_size=4, max_tokens=5)

10
tests/e2e/310p/singlecard/test_vl_model_singlecard.py
View File

@@ -15,20 +15,18 @@
# limitations under the License.
# This file is a part of the vllm-ascend project.
import sys
import os
import sys
# Add 310p directory to sys.path
current_dir = os.path.dirname(os.path.abspath(__file__))
parent_dir = os.path.dirname(current_dir) # 310p directory
sys.path.insert(0, parent_dir)
# ruff: noqa: E402
from test_utils import run_vl_model_test
def test_qwen3_vl_8b_tp1_fp16():
"""Qwen3-VL-8B single-card FP16 test"""
run_vl_model_test(
model_name="Qwen/Qwen3-VL-8B-Instruct",
tensor_parallel_size=1,
max_tokens=5
)
run_vl_model_test(model_name="Qwen/Qwen3-VL-8B-Instruct", tensor_parallel_size=1, max_tokens=5)

23
tests/e2e/310p/test_utils.py
View File

@@ -15,10 +15,12 @@
# limitations under the License.
# This file is a part of the vllm-ascend project.
from tests.e2e.conftest import VllmRunner
from PIL import Image
import os
from PIL import Image
from tests.e2e.conftest import VllmRunner
def get_test_image():
"""Get the image object for testing"""
@@ -32,14 +34,12 @@ def get_test_prompts():
return ["<|image_pad|>Describe this image in detail."]
def run_vl_model_test(model_name: str,
tensor_parallel_size: int,
max_tokens: int,
dtype: str = "float16",
enforce_eager: bool = True):
def run_vl_model_test(
model_name: str, tensor_parallel_size: int, max_tokens: int, dtype: str = "float16", enforce_eager: bool = True
):
"""
Generic visual language model test function
Args:
model_name: Model name, e.g., "Qwen/Qwen3-VL-4B"
tensor_parallel_size: Tensor parallel size
@@ -52,9 +52,6 @@ def run_vl_model_test(model_name: str,
prompts = get_test_prompts()
with VllmRunner(
model_name,
tensor_parallel_size=tensor_parallel_size,
enforce_eager=enforce_eager,
dtype=dtype
model_name, tensor_parallel_size=tensor_parallel_size, enforce_eager=enforce_eager, dtype=dtype
) as vllm_model:
vllm_model.generate_greedy(prompts, max_tokens, images=images)
vllm_model.generate_greedy(prompts, max_tokens, images=images)