EricLBuehler/candle-vllm
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
Unified framework for building enterprise RAG pipelines with small, specialized models
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
Access large language models from the command-line
Evaluate the accuracy of LLM generated outputs
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
LLM inference in C/C++
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
1 capture since 2026-05-25
AI agent config detected
Key config paths
docs/components/agents.md
docs/examples/agents.md