Skip to content
View Ramshankar07's full-sized avatar
🎯
Open To Work
🎯
Open To Work

Highlights

  • Pro

Block or report Ramshankar07

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Ramshankar07/README.md

Hi 👋, I'm Ramshankar

ramshankar07

Research Interests

  • GPU kernel optimization and low-level performance engineering
  • Model quantization and precision-efficient inference

💻 Tech Stack

Python MySQL R C++

NumPy Pandas scikit-learn Keras TensorFlow PyTorch Langchain Library Hugging Face

AWS Google Cloud CUDA Docker

Pinned Loading

  1. CUDA-llama3.1-inference CUDA-llama3.1-inference Public

    This repository is CUDA implementation for LLAMA 3.1 open models

    Cuda 2

  2. qwen600-ROCm-inference qwen600-ROCm-inference Public

    Forked from yassa9/qwen600

    Static suckless single batch qwen3-0.6B mini inference engine

    C++ 1

  3. Fintech-Data-Processing-ETL-Platform Fintech-Data-Processing-ETL-Platform Public

    Assignment 02 for the course work DAMG7245-Spring 2025

    Jupyter Notebook

  4. Parallelizing-Text-to-Image-Generation Parallelizing-Text-to-Image-Generation Public

    Explore the feasibility and performance characteristics of using multiple CPUs versus GPUs for preprocessing tasks in text-to-image generation pipelines. Compare speedup, efficiency, and cost to id…

    Jupyter Notebook

  5. Real-Time-TTS-FastPitch-Finetune Real-Time-TTS-FastPitch-Finetune Public

    Python

  6. RecSys-Transformer-for-Food RecSys-Transformer-for-Food Public

    Jupyter Notebook