mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-15 07:24:57 +08:00
e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
96 lines
3.3 KiB
Python
96 lines
3.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
from typing import List, Optional, Tuple, Union
|
|
|
|
from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
|
|
DeltaMessage)
|
|
from vllm.entrypoints.openai.reasoning_parsers import ReasoningParser
|
|
|
|
|
|
class StreamingReasoningReconstructor:
|
|
|
|
def __init__(self):
|
|
self.reasoning_content = None
|
|
self.other_content = None
|
|
|
|
def append_delta(self, delta: DeltaMessage):
|
|
# content and the reasoning content should not be present
|
|
# at the same time
|
|
assert delta.content is None or delta.reasoning_content is None, (
|
|
"Both content and reasoning content are present in the "
|
|
"delta message")
|
|
if delta.content is not None:
|
|
if self.other_content is None:
|
|
self.other_content = delta.content
|
|
else:
|
|
self.other_content += delta.content
|
|
else:
|
|
if self.reasoning_content is None:
|
|
self.reasoning_content = delta.reasoning_content
|
|
else:
|
|
self.reasoning_content += delta.reasoning_content
|
|
|
|
|
|
def run_reasoning_extraction(
|
|
reasoning_parser: ReasoningParser,
|
|
model_output: List[str],
|
|
request: Union[ChatCompletionRequest, None] = None,
|
|
streaming: bool = False,
|
|
) -> Tuple[Optional[str], Optional[str]]:
|
|
if streaming:
|
|
reconstructor = run_reasoning_extraction_streaming(
|
|
reasoning_parser,
|
|
model_output,
|
|
request,
|
|
)
|
|
return (
|
|
reconstructor.reasoning_content,
|
|
reconstructor.other_content or None,
|
|
)
|
|
else:
|
|
reasoning, content = run_reasoning_extraction_nonstreaming(
|
|
reasoning_parser, model_output, request)
|
|
return reasoning, content
|
|
|
|
|
|
def run_reasoning_extraction_nonstreaming(
|
|
reasoning_parser: ReasoningParser,
|
|
model_output: List[str],
|
|
request: Union[ChatCompletionRequest, None] = None,
|
|
) -> Tuple[Optional[str], Optional[str]]:
|
|
request = request or ChatCompletionRequest(messages=[], model="test-model")
|
|
return reasoning_parser.extract_reasoning_content(
|
|
model_output=''.join(model_output), request=request)
|
|
|
|
|
|
def run_reasoning_extraction_streaming(
|
|
reasoning_parser: ReasoningParser,
|
|
model_deltas: List[str],
|
|
request: Union[ChatCompletionRequest, None] = None,
|
|
) -> StreamingReasoningReconstructor:
|
|
request = request or ChatCompletionRequest(messages=[], model="test-model")
|
|
reconstructor = StreamingReasoningReconstructor()
|
|
previous_text = ""
|
|
previous_tokens: List[int] = []
|
|
for delta in model_deltas:
|
|
token_delta = [
|
|
reasoning_parser.vocab.get(token)
|
|
for token in reasoning_parser.model_tokenizer.tokenize(delta)
|
|
if token in reasoning_parser.vocab
|
|
]
|
|
current_text = previous_text + delta
|
|
current_tokens = previous_tokens + token_delta
|
|
delta_message = reasoning_parser.extract_reasoning_content_streaming(
|
|
previous_text,
|
|
current_text,
|
|
delta,
|
|
previous_tokens,
|
|
current_tokens,
|
|
token_delta,
|
|
)
|
|
if delta_message is not None:
|
|
reconstructor.append_delta(delta_message)
|
|
previous_text = current_text
|
|
previous_tokens = current_tokens
|
|
return reconstructor
|