Pinned Loading

1. cuda-kv-cache-compression cuda-kv-cache-compression Public

   High-performance CUDA implementation of per-channel INT8 KV-cache quantization, exploring memory-bound optimizations including tiling, thread coarsening, and vectorized loads.

   Cuda

2. inmemorykb inmemorykb Public

   In Memory Knowledge Base for Agents

   Python

3. LocalLanguageModels LocalLanguageModels Public

   Experimenting with running SLM/LLMs locally, using the huggingface transformers.

   Jupyter Notebook

4. ray-tracer ray-tracer Public

   A work-in-progress Path Tracer based on Peter Shirley's book, currently using a naive brute force ray tracing algorithm, can simulate Lambert, Metallic, and Transparent objects.

   C++

5. Override3D Override3D Public

   Override3D is a 3D rendering engine I'm in the process of creating, as of now it simply exists as a decent enough foundation and boilerplate.

   C

6. MediaLibrary MediaLibrary Public

   A work-in-progress media manipulation API written in C flavoured C++ using FFMPEG LibAV, currently capable of encoding, decoding, remuxing and transcoding files with a simple interface.

   C++