🎯 Use Case Hermes Skill

serving-llms-vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

仓库: NousResearch/hermes-agent · v1.0.1 · by Orchestra Research · MIT

vLLMInference ServingPagedAttentionContinuous BatchingHigh ThroughputProductionOpenAI APIQuantizationTensor Parallelism

文件路径

skills/mlops/inference/serving-llms-vllm/SKILL.md