Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
41 lines
1.0 KiB
Python
41 lines
1.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Example Python client for embedding API using vLLM API server
|
|
NOTE:
|
|
start a supported embeddings model server with `vllm serve`, e.g.
|
|
vllm serve intfloat/e5-small
|
|
"""
|
|
|
|
from openai import OpenAI
|
|
|
|
# Modify OpenAI's API key and API base to use vLLM's API server.
|
|
openai_api_key = "EMPTY"
|
|
openai_api_base = "http://localhost:8000/v1"
|
|
|
|
|
|
def main():
|
|
client = OpenAI(
|
|
# defaults to os.environ.get("OPENAI_API_KEY")
|
|
api_key=openai_api_key,
|
|
base_url=openai_api_base,
|
|
)
|
|
|
|
models = client.models.list()
|
|
model = models.data[0].id
|
|
|
|
responses = client.embeddings.create(
|
|
# ruff: noqa: E501
|
|
input=[
|
|
"Hello my name is",
|
|
"The best thing about vLLM is that it supports many different models",
|
|
],
|
|
model=model,
|
|
)
|
|
|
|
for data in responses.data:
|
|
print(data.embedding) # List of float of len 4096
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|