Popular repositories Loading

1. vllm-turboquant-gb10 vllm-turboquant-gb10 Public

   Build guide for vLLM 0.18.1 with TurboQuant KV cache compression on NVIDIA GB10 (Grace Blackwell) aarch64 / CUDA 13.0 / SM 12.1

2. gb10-nccl-switched-fabric gb10-nccl-switched-fabric Public

   practical guide to multi-node NCCL over switched RoCE fabric on NVIDIA GB10 (DGX Spark class) — documenting the gaps in NVIDIA's official playbooks

3. the-forge the-forge Public

   Multi-model orchestrated inference platform — LangGraph state machine routing queries across three GPU nodes over a 200Gbps RoCE fabric

   Python

4. Local-RAG-Engine-Private-Document-Intelligence-with-Gemma-4 Local-RAG-Engine-Private-Document-Intelligence-with-Gemma-4 Public

   A lightweight, high-performance Retrieval-Augmented Generation (RAG) pipeline designed to run entirely offline on macOS. This system allows users to perform conversational AI queries against a priv…

   Python