vLLM 是一款专为大语言模型推理加速而设计的框架实现了 KV 缓存内存几乎零浪费解决了内存管理瓶颈问题。更多 vLLM 中文文档及教程可访问 →go.hyper.ai/Wa62f本目录包含用于部署 vLLM 应用程序的 Helm 图表。该图表包含部署配置、自动扩缩容、资源管理及其他相关配置项。*在线运行 vLLM 入门教程零基础分步指南源码 examples/online_serving/cohere_rerank_client.py# SPDX-License-Identifier: Apache-2.0 使用 OpenAI 入口点的 Rerank API 的示例 该 API 兼容Cohere SDK:https://github.com/cohere-ai/cohere-python run: vllm serve BAAI/bge-reranker-base import cohere# cohere v1 client# cohere v1 客户端co cohere.Client(base_urlhttp://localhost:8000, api_keysk-fake-key) rerank_v1_result co.rerank( modelBAAI/bge-reranker-base, queryWhat is the capital of France?, documents[ The capital of France is Paris, Reranking is fun!, vLLM is an open-source framework for fast AI serving ]) print(rerank_v1_result)# or the v2# 或 V2co2 cohere.ClientV2(sk-fake-key, base_urlhttp://localhost:8000) v2_rerank_result co2.rerank( modelBAAI/bge-reranker-base, queryWhat is the capital of France?, documents[ The capital of France is Paris, Reranking is fun!, vLLM is an open-source framework for fast AI serving ]) print(v2_rerank_result)