Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, d
Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.
Marketplace
Independent
Category
operations
More like this
Browse operations agents →
Asana Intelligence
AI built into Asana to accelerate team execution
$10.99/mo
operationsLayer
Build visual tree structures of your projects and goals in just a few clicks
Free · Paid plans available
operationsEraser
Generate AI diagrams and docs from simple text prompts
Free · Paid plans available
operationsDocumind
Open-source platform for extracting structured data from documents
Free · Paid plans available