Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Harry Mellor <hej.mellor@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
804e5377aa
commit
8c1557a79c
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
This example shows how to use vLLM for running offline inference
|
||||
"""This example shows how to use vLLM for running offline inference
|
||||
with the correct prompt format on audio language models.
|
||||
|
||||
For most models, the prompt format should follow corresponding examples
|
||||
@@ -286,8 +285,7 @@ def run_minicpmo(question: str, audio_count: int) -> ModelRequestData:
|
||||
|
||||
# Phi-4-multimodal-instruct
|
||||
def run_phi4mm(question: str, audio_count: int) -> ModelRequestData:
|
||||
"""
|
||||
Phi-4-multimodal-instruct supports both image and audio inputs. Here, we
|
||||
"""Phi-4-multimodal-instruct supports both image and audio inputs. Here, we
|
||||
show how to process audio inputs.
|
||||
"""
|
||||
model_path = snapshot_download("microsoft/Phi-4-multimodal-instruct")
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
This example shows how to use vLLM for running offline inference with
|
||||
"""This example shows how to use vLLM for running offline inference with
|
||||
the explicit/implicit prompt format on enc-dec LMMs for text generation.
|
||||
"""
|
||||
|
||||
@@ -56,8 +55,7 @@ def run_whisper():
|
||||
|
||||
|
||||
def run_fireredasr2():
|
||||
"""
|
||||
FireRedASR2 – Automatic Speech Recognition model.
|
||||
"""FireRedASR2 – Automatic Speech Recognition model.
|
||||
|
||||
This model uses a Conformer encoder + Qwen2 LLM decoder architecture
|
||||
for speech-to-text transcription. Audio is passed via the implicit
|
||||
|
||||
@@ -43,7 +43,6 @@ headers = {"User-Agent": "vLLM Example Client"}
|
||||
|
||||
def encode_base64_content_from_url(content_url: str) -> str:
|
||||
"""Encode a content retrieved from a remote url to base64 format."""
|
||||
|
||||
with requests.get(content_url, headers=headers) as response:
|
||||
response.raise_for_status()
|
||||
result = base64.b64encode(response.content).decode("utf-8")
|
||||
@@ -53,7 +52,6 @@ def encode_base64_content_from_url(content_url: str) -> str:
|
||||
|
||||
def encode_base64_content_from_file(file_path: str) -> str:
|
||||
"""Encode a local file content to base64 format."""
|
||||
|
||||
with open(file_path, "rb") as file:
|
||||
file_content = file.read()
|
||||
result = base64.b64encode(file_content).decode("utf-8")
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
This example shows how to use vLLM for running offline inference
|
||||
"""This example shows how to use vLLM for running offline inference
|
||||
with the correct prompt format on Qwen2.5-Omni (thinker only).
|
||||
"""
|
||||
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
This example shows how to use vLLM for running offline inference
|
||||
"""This example shows how to use vLLM for running offline inference
|
||||
with the correct prompt format on Qwen3-Omni (thinker only).
|
||||
"""
|
||||
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
This example shows how to use vLLM for running offline inference with
|
||||
"""This example shows how to use vLLM for running offline inference with
|
||||
multi-image input on vision language models for text generation,
|
||||
using the chat template defined by the model.
|
||||
"""
|
||||
@@ -913,11 +912,9 @@ def load_phi3v(question: str, image_urls: list[str]) -> ModelRequestData:
|
||||
|
||||
|
||||
def load_phi4mm(question: str, image_urls: list[str]) -> ModelRequestData:
|
||||
"""
|
||||
Phi-4-multimodal-instruct supports both image and audio inputs. Here, we
|
||||
"""Phi-4-multimodal-instruct supports both image and audio inputs. Here, we
|
||||
show how to process multi images inputs.
|
||||
"""
|
||||
|
||||
model_path = snapshot_download("microsoft/Phi-4-multimodal-instruct")
|
||||
# Since the vision-lora and speech-lora co-exist with the base model,
|
||||
# we have to manually specify the path of the lora weights.
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
This example shows how to use vLLM for running offline inference with
|
||||
"""This example shows how to use vLLM for running offline inference with
|
||||
the correct prompt format on vision language models for text generation.
|
||||
|
||||
For most models, the prompt format should follow corresponding examples
|
||||
@@ -1660,8 +1659,7 @@ def run_phi3v(questions: list[str], modality: str) -> ModelRequestData:
|
||||
|
||||
# Phi-4-multimodal-instruct
|
||||
def run_phi4mm(questions: list[str], modality: str) -> ModelRequestData:
|
||||
"""
|
||||
Phi-4-multimodal-instruct supports both image and audio inputs. Here, we
|
||||
"""Phi-4-multimodal-instruct supports both image and audio inputs. Here, we
|
||||
show how to process image inputs.
|
||||
"""
|
||||
assert modality == "image"
|
||||
@@ -2283,8 +2281,7 @@ MODELS_SUPPORT_VIT_CUDA_GRAPH = [
|
||||
|
||||
|
||||
def get_multi_modal_input(args):
|
||||
"""
|
||||
return {
|
||||
"""Return {
|
||||
"data": image or video,
|
||||
"question": question,
|
||||
}
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
Trace-replay with vLLM offline inference.
|
||||
"""Trace-replay with vLLM offline inference.
|
||||
|
||||
Trace-replay lets you supply a known sequence of decode token IDs alongside
|
||||
the prompt. Instead of sampling from the model distribution, the engine
|
||||
|
||||
Reference in New Issue
Block a user