Pinned Loading

1. waqasm86.github.io waqasm86.github.io Public

   Personal engineering portfolio showcasing CUDA + C++ + LLM inference projects. Features production-grade distributed systems, empirical performance research, and on-device AI optimization. Built wi…

2. llcuda llcuda Public

   CUDA-accelerated LLM inference for Python with automatic server management. Zero-configuration setup, JupyterLab-ready, production-grade performance. Just install and start inferencing!

   Python

3. Ubuntu-Cuda-Llama.cpp-Executable Ubuntu-Cuda-Llama.cpp-Executable Public

   Pre-built llama.cpp CUDA binary for Ubuntu 22.04. No compilation required - download, extract, and run! Works with llcuda Python package for JupyterLab integration. Tested on GeForce 940M to RTX 4090.

   Python 1

4. cuda-nvidia-systems-engg cuda-nvidia-systems-engg Public

   Production-grade C++20/CUDA distributed LLM inference system with TCP networking, MPI scheduling, and content-addressed storage. Features comprehensive benchmarking (p50/p95/p99 latencies), epoll a…

   C++

5. cuda-tcp-llama.cpp cuda-tcp-llama.cpp Public

   High-performance TCP inference gateway with epoll async I/O for CUDA-accelerated LLM serving. Binary protocol, connection pooling, streaming responses. Zero dependencies beyond POSIX and CUDA.

   C++

6. cuda-llm-storage-pipeline cuda-llm-storage-pipeline Public

   Content-addressed LLM model distribution with SHA256 verification and SeaweedFS integration. Distributed storage, manifest management, LRU caching, and integrity checking for GGUF models.

   C++