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

[Lint]Style: Convert test/ to ruff format(Batch #5) (#6747)

Browse Source 
### What this PR does / why we need it?
| File Path |
| :--- |
| `tests/e2e/singlecard/compile/backend.py` |
| `tests/e2e/singlecard/compile/test_graphex_norm_quant_fusion.py` |
| `tests/e2e/singlecard/compile/test_graphex_qknorm_rope_fusion.py` |
| `tests/e2e/singlecard/compile/test_norm_quant_fusion.py` |
| `tests/e2e/singlecard/model_runner_v2/test_basic.py` |
| `tests/e2e/singlecard/test_aclgraph_accuracy.py` |
| `tests/e2e/singlecard/test_aclgraph_batch_invariant.py` |
| `tests/e2e/singlecard/test_aclgraph_mem.py` |
| `tests/e2e/singlecard/test_async_scheduling.py` |
| `tests/e2e/singlecard/test_auto_fit_max_mode_len.py` |
| `tests/e2e/singlecard/test_batch_invariant.py` |
| `tests/e2e/singlecard/test_camem.py` |
| `tests/e2e/singlecard/test_completion_with_prompt_embeds.py` |
| `tests/e2e/singlecard/test_cpu_offloading.py` |
| `tests/e2e/singlecard/test_guided_decoding.py` |
| `tests/e2e/singlecard/test_ilama_lora.py` |
| `tests/e2e/singlecard/test_llama32_lora.py` |
| `tests/e2e/singlecard/test_models.py` |
| `tests/e2e/singlecard/test_multistream_overlap_shared_expert.py` |
| `tests/e2e/singlecard/test_quantization.py` |
| `tests/e2e/singlecard/test_qwen3_multi_loras.py` |
| `tests/e2e/singlecard/test_sampler.py` |
| `tests/e2e/singlecard/test_vlm.py` |
| `tests/e2e/singlecard/test_xlite.py` |
| `tests/e2e/singlecard/utils.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>
This commit is contained in:
SILONG ZENG
2026-02-24 15:50:00 +08:00
committed by GitHub
parent 747484cb64
commit 62ea664aa7
26 changed files with 859 additions and 1052 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
tests/e2e/singlecard/test_llama32_lora.py
View File

@@ -1,12 +1,12 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import pytest
from unittest.mock import patch
import pytest
import vllm
import vllm.config
from vllm.lora.request import LoRARequest
from unittest.mock import patch
from tests.e2e.conftest import VllmRunner
from vllm_ascend.utils import enable_custom_op
@@ -53,17 +53,12 @@ def do_sample(
PROMPT_TEMPLATE.format(context="How many candidates are there?"),
PROMPT_TEMPLATE.format(context="Count the number of candidates."),
PROMPT_TEMPLATE.format(
context=
"Which poll resource provided the most number of candidate information?" # noqa: E501
context="Which poll resource provided the most number of candidate information?" # noqa: E501
),
PROMPT_TEMPLATE.format(
context=
"Return the poll resource associated with the most candidates."),
PROMPT_TEMPLATE.format(context="Return the poll resource associated with the most candidates."),
]
sampling_params = vllm.SamplingParams(temperature=0,
max_tokens=64,
stop=["<|im_end|>"])
sampling_params = vllm.SamplingParams(temperature=0, max_tokens=64, stop=["<|im_end|>"])
if tensorizer_config_dict is not None:
outputs = llm.generate(
prompts,
@@ -73,14 +68,15 @@ def do_sample(
lora_id,
lora_path,
tensorizer_config_dict=tensorizer_config_dict,
) if lora_id else None,
)
if lora_id
else None,
)
else:
outputs = llm.generate(
prompts,
sampling_params,
lora_request=LoRARequest(str(lora_id), lora_id, lora_path)
if lora_id else None,
lora_request=LoRARequest(str(lora_id), lora_id, lora_path) if lora_id else None,
)
generated_texts: list[str] = []
@@ -92,33 +88,40 @@ def do_sample(
return generated_texts
def generate_and_test(llm,
llama32_lora_files,
tensorizer_config_dict: dict | None = None):
def generate_and_test(llm, llama32_lora_files, tensorizer_config_dict: dict | None = None):
print("lora adapter created")
print("lora 1")
assert (do_sample(
llm,
llama32_lora_files,
tensorizer_config_dict=tensorizer_config_dict,
lora_id=1,
) == EXPECTED_LORA_OUTPUT)
assert (
do_sample(
llm,
llama32_lora_files,
tensorizer_config_dict=tensorizer_config_dict,
lora_id=1,
)
== EXPECTED_LORA_OUTPUT
)
print("lora 2")
assert (do_sample(
llm,
llama32_lora_files,
tensorizer_config_dict=tensorizer_config_dict,
lora_id=2,
) == EXPECTED_LORA_OUTPUT)
assert (
do_sample(
llm,
llama32_lora_files,
tensorizer_config_dict=tensorizer_config_dict,
lora_id=2,
)
== EXPECTED_LORA_OUTPUT
)
print("base model")
assert (do_sample(
llm,
llama32_lora_files,
tensorizer_config_dict=tensorizer_config_dict,
lora_id=0,
) == EXPECTED_BASE_MODEL_OUTPUT)
assert (
do_sample(
llm,
llama32_lora_files,
tensorizer_config_dict=tensorizer_config_dict,
lora_id=0,
)
== EXPECTED_BASE_MODEL_OUTPUT
)
print("removing lora")