Pinned Loading

1. MCP-Ollama-Client MCP-Ollama-Client Public

   Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json

   Python 7 2

2. CUDA-Custom-Kernels CUDA-Custom-Kernels Public

   Contains my CUDA kernels implementations and benchmarking like Tiled Matrix Multiplication for learning.

   Cuda

3. ECE-GY-9143---High-Performance-Machine-Learning ECE-GY-9143---High-Performance-Machine-Learning Public

   Contains laboratory and project work for the course ECE-GY 9143 - High Performance Machine Learning

   Python 3 1

4. Flash-Attention-Triton Flash-Attention-Triton Public

   This repository contains the codebase for the Flash Attention implementation on Triton.

   Python

5. MLIR-to-PTX-CUDA MLIR-to-PTX-CUDA Public

   Creating an MLIR dialect that fuses Addition + ReLU, lowers to NVVM and LLVM IR and generates PTX to run the kernel on CUDA GPU

   C++

6. Multimodal-Architecture-Optimisation-on-RTX3060-using-TVM Multimodal-Architecture-Optimisation-on-RTX3060-using-TVM Public

   This repository contains the codebase for optimizing a Vision to Text model on a target RTX3060 device using Apache TVM

   Python