NetEase-Media/grps_trtllm
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.
ORIGINAL REPOSITORY
NetEase-Media/grps_trtllm ↗GitHub activity
- Stars
- 161
- Forks
- 12
- Open issues and PRs
- 7
- Repository size
- ~141,893 KB
- Default branch
- master
- Created
- Aug 21, 2024
- Repository updated
- Aug 6, 2026
- Last push
- Dec 7, 2025
- Language
- Python
- License
- Apache-2.0
Topics ai-agent · chatglm · deepseek-r1 · function-call · internvideo · internvl · janus-pro · llama-index · llama3 · llm · minicpm-v · multi-modal
Repository-wide figures from GitHub, checked Nov 3, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Original repository
- NetEase-Media/grps_trtllm
- Credit basis
- GitHub repository owner or organization; individual authorship is not asserted
- Publisher
- NetEase-Media
- Upstream last modified
- Aug 6, 2026
- Official website
- https://github.com/NetEase-Media/grps_trtllm
- Languages
- Python
- Access
- Open original GitHub repository; publisher terms apply
- Last checked
- Nov 3, 2026
- License
- Apache-2.0
- Last record update
- Nov 3, 2026