Fix per file ruff ignores related to line length (#26262)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-06 05:12:40 +00:00
committed by GitHub
parent 91ac7f764d
commit 6c04638214
65 changed files with 301 additions and 291 deletions
+7 -7
View File
@@ -134,15 +134,15 @@ def get_attention_backend(backend_name: _Backend):
else "vllm.v1.attention.backends.rocm_aiter_fa.AiterFlashAttentionBackend"
),
_Backend.FLASHINFER: "vllm.v1.attention.backends.flashinfer.FlashInferBackend",
_Backend.FLEX_ATTENTION: "vllm.v1.attention.backends.flex_attention.FlexAttentionBackend",
_Backend.TRITON_ATTN: "vllm.v1.attention.backends.triton_attn.TritonAttentionBackend",
_Backend.FLEX_ATTENTION: "vllm.v1.attention.backends.flex_attention.FlexAttentionBackend", # noqa: E501
_Backend.TRITON_ATTN: "vllm.v1.attention.backends.triton_attn.TritonAttentionBackend", # noqa: E501
_Backend.TREE_ATTN: "vllm.v1.attention.backends.tree_attn.TreeAttentionBackend",
_Backend.XFORMERS: "vllm.v1.attention.backends.xformers.XFormersAttentionBackend",
_Backend.CUTLASS_MLA: "vllm.v1.attention.backends.mla.cutlass_mla.CutlassMLABackend",
_Backend.XFORMERS: "vllm.v1.attention.backends.xformers.XFormersAttentionBackend", # noqa: E501
_Backend.CUTLASS_MLA: "vllm.v1.attention.backends.mla.cutlass_mla.CutlassMLABackend", # noqa: E501
_Backend.FLASHMLA: "vllm.v1.attention.backends.mla.flashmla.FlashMLABackend",
_Backend.FLASH_ATTN_MLA: "vllm.v1.attention.backends.mla.flashattn_mla.FlashAttnMLABackend",
_Backend.FLASHINFER_MLA: "vllm.v1.attention.backends.mla.flashinfer_mla.FlashInferMLABackend",
_Backend.TRITON_MLA: "vllm.v1.attention.backends.mla.triton_mla.TritonMLABackend",
_Backend.FLASH_ATTN_MLA: "vllm.v1.attention.backends.mla.flashattn_mla.FlashAttnMLABackend", # noqa: E501
_Backend.FLASHINFER_MLA: "vllm.v1.attention.backends.mla.flashinfer_mla.FlashInferMLABackend", # noqa: E501
_Backend.TRITON_MLA: "vllm.v1.attention.backends.mla.triton_mla.TritonMLABackend", # noqa: E501
}
if backend_name not in backend_map:
@@ -104,7 +104,7 @@ async def test_single_chat_session_image_base64encoded(
"content": [
{
"type": "input_image",
"image_url": f"data:image/jpeg;base64,{base64_encoded_image[raw_image_url]}",
"image_url": f"data:image/jpeg;base64,{base64_encoded_image[raw_image_url]}", # noqa: E501
"detail": "auto",
},
{"type": "input_text", "text": content_text},
@@ -15,8 +15,9 @@ RTOL = 0.03
EXPECTED_VALUES = {"Qwen/Qwen3-0.6B": 0.41, "deepseek-ai/deepseek-vl2-small": 0.59}
SIMPLE_PROMPT = (
"The best part about working on vLLM is that I got to meet so many people across various different organizations like UCB, Google, and Meta which means",
) # noqa: E501
"The best part about working on vLLM is that I got to meet so many people across "
"various different organizations like UCB, Google, and Meta which means",
)
# Get model name from environment variable
MODEL_NAME = os.environ.get("TEST_MODEL", "Qwen/Qwen3-0.6B")
@@ -127,7 +127,7 @@ class RequestRunner:
kv_role="kv_both",
kv_connector_extra_config={
"spec_name": "MockOffloadingSpec",
"spec_module_path": "tests.v1.kv_connector.unit.test_offloading_connector",
"spec_module_path": "tests.v1.kv_connector.unit.test_offloading_connector", # noqa: E501
"block_size": offloaded_block_size,
},
)
@@ -260,15 +260,8 @@ def test_pooling_rejects_custom_logitsprocs(
gpu_memory_utilization=0.1,
)
# Require that no logitsprocs have been loaded
assert (
sum(
[
1
for _ in llm.llm_engine.model_executor.driver_worker.worker.model_runner.input_batch.logitsprocs.all
]
)
== 0
)
worker = llm.llm_engine.model_executor.driver_worker.worker
assert sum([1 for _ in worker.model_runner.input_batch.logitsprocs.all]) == 0
return
kwargs: dict[str, list[Union[str, type[LogitsProcessor]]]] = {}