Popular repositories Loading

1. cuhk-x-multimodal-vqa cuhk-x-multimodal-vqa Public

   Reproducible solo solution workspace for the CUHK-X Large Model Track

   Python 2

2. llm-gateway llm-gateway Public

   Lightweight OpenAI-compatible LLM gateway: multi-upstream routing, managed credentials, and real-time token accounting with a live dashboard.

   Go 2

3. luicarus luicarus Public

   Profile

   1

4. ray ray Public

   Forked from ray-project/ray

   Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

   Python

5. pegainfer pegainfer Public

   Forked from pegainfer-project/pegainfer

   Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

   Rust

6. small-gpu-vlm-inference small-gpu-vlm-inference Public

   Small-GPU VLM inference experiments on a 4 GB RTX 3050 Ti: vLLM memory boundaries, engine comparison, and prefix caching, with raw data and measurement pitfalls

   Python