Skip to content
View krishnateja95's full-sized avatar

Block or report krishnateja95

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
krishnateja95/README.md

Krishna Teja Chitty-Venkata

Hi there! My name is Krishna Teja Chitty-Venkata. I am a Machine Learning Research Engineer at Red Hat. I work primarily on efficient LLM inference. Prior to Red Hat, I was a Postdoctoral Researcher at Argonne National Laboratory (US Department of Energy, Office of Science). I obtained my PhD at Iowa State University.

Research Interests:

Broadly, I am interested in optimizing Deep Learning models on Hardware accelerators.

  • Large Language and Multimodal Model Optimization
  • Efficient Finetuning and Inference methods
  • Hardware-aware Neural Architecture Search
  • Pruning, Quantization, KV Cache eviction
  • High Performance Computing for AI
  • Performance Benchmarking
  • AI for science applications

Education:

  • Iowa State University, Ames, Iowa, USA

    • Doctor of Philosophy (PhD)
    • Department of Electrical and Computer Engineering
    • August 2017 - July 2023
    • Dissertation Title: Hardware-aware Design, Search and Optimization of Deep Neural Networks
    • PhD Supervisor: Prof. Dr. Arun Somani
  • University College of Engineering, Osmania University, Hyderabad, India

    • Bachelor of Engineering
    • Electronics and Communication Engineering
    • 2013 - 2017

Pinned Loading

  1. argonne-lcf/LLM-Inference-Bench argonne-lcf/LLM-Inference-Bench Public

    LLM-Inference-Bench

    Jupyter Notebook 57 7

  2. WActiGrad WActiGrad Public

    Python

  3. LangVision-NAS LangVision-NAS Public

    Code of the paper "LANGVISION-LORA-NAS: NEURAL ARCHITECTURE SEARCH FOR VARIABLE LORA RANK IN VISION LANGUAGE MODELS"

    Python 1

  4. MoE-Mixed-Prec MoE-Mixed-Prec Public

    MoPEQ [Code Cleanup Pending]

    Python

  5. MoE-Varying-TopK MoE-Varying-TopK Public

    Python