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

34
tests/e2e/multicard/2-cards/test_quantization.py
View File

@@ -16,7 +16,6 @@
# This file is a part of the vllm-ascend project.
# Adapted from vllm/tests/basic_correctness/test_basic_correctness.py
#
import pytest
from tests.e2e.conftest import VllmRunner
@@ -27,16 +26,16 @@ def test_qwen2_5_w8a8_external_quantized_tp2():
]
max_tokens = 5
with VllmRunner(
"neuralmagic/Qwen2.5-3B-quantized.w8a8",
tensor_parallel_size=2,
cudagraph_capture_sizes=[1, 2, 4, 8],
max_model_len=4096,
gpu_memory_utilization=0.8,
"neuralmagic/Qwen2.5-3B-quantized.w8a8",
tensor_parallel_size=2,
cudagraph_capture_sizes=[1, 2, 4, 8],
max_model_len=4096,
gpu_memory_utilization=0.8,
) as vllm_model:
vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)
golden_results = [
'The president of the United States is the head of state and',
"The president of the United States is the head of state and",
]
for i in range(len(vllm_output)):
@@ -50,36 +49,37 @@ def test_qwen3_moe_w8a8_dynamic_llm_compressor():
]
max_tokens = 5
with VllmRunner(
"vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w8a8",
tensor_parallel_size=2,
max_model_len=4096,
gpu_memory_utilization=0.8,
"vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w8a8",
tensor_parallel_size=2,
max_model_len=4096,
gpu_memory_utilization=0.8,
) as vllm_model:
vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)
golden_results = [
'The president of the United States is the head of state and',
"The president of the United States is the head of state and",
]
for i in range(len(vllm_output)):
assert golden_results[i] == vllm_output[i][1]
print(f"Generated text: {vllm_output[i][1]!r}")
def test_qwen3_moe_w4a8_dynamic_llm_compressor():
example_prompts = [
"The president of the United States is",
]
max_tokens = 5
with VllmRunner(
"vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w4a8",
tensor_parallel_size=2,
max_model_len=4096,
gpu_memory_utilization=0.8,
"vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w4a8",
tensor_parallel_size=2,
max_model_len=4096,
gpu_memory_utilization=0.8,
) as vllm_model:
vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)
golden_results = [
'The president of the United States is the head of state and',
"The president of the United States is the head of state and",
]
for i in range(len(vllm_output)):