Skip to content
View UsamaKenway's full-sized avatar

Organizations

@AICU-HEALTH

Block or report UsamaKenway

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
UsamaKenway/README.md

Hi 👋, I'm Usama

usamakenway

🔭 My projects

🏠 My Hobby Domain

Open Source Contributions

Repository PR|Branch Status Date
huggingface/transformers Halving the CPU Ram usage during GGUF Dequantization Merged Apr 2026
vllm-project/vllm Add GGUF Support to Gemma (31B & 26B-A4B) gaining 1.5x on concurrent request compared to llama.cpp Upcoming Apr 2026
huggingface/transformers Add GGUF support to Gemma4 (31B & 26B-A4B) Approved Apr 2026
vllm-project/vllm-omni Add Qwen2.5-Omni-3B model inference support Merged Feb 2026
huggingface/huggingface.js Added specs for RTX 5000 series, L40s, mobile GPUs Merged Feb 2025
oobabooga/text-generation-webui Add custom model auto downloader from Hugging Face Merged Apr 2023

Writings

📬Connect with Me📬

Tech Stack

Data & Persistence

PostgreSQL MySQL SQLite Redis SQLAlchemy Pandas NumPy ETL Scraping ORMs

Machine Learning & Optimization

PyTorch scikit-learn Transformers Accelerate ONNX TensorRT Prophet LoRA/DoRA BitsandBytes AWQ GGUF llama.cpp DDP/FSDP NVFP4

NLP & LLMs

LangChain SpaCy Ragas RAG Vector Databases Embeddings LLM Eval Tokenizing

Computer Vision & Generative Media

OpenCV YOLO Stable Diffusion Flux StyleGAN ControlNet IP-Adapter AnimateDiff Text-to-Video Vid2Vid Qwen3 TTS

Cloud, DevOps & MLOps

Python AWS FastAPI Django Docker GitHub Actions MLflow vLLM Runpod HF Endpoints TensorRT LLM Linux

AWS Ecosystem

S3 EC2 ECS ECR Lambda Fargate Elastic Beanstalk

Data Visualization

Matplotlib Seaborn Plotly W&B

usamakenway

 usamakenway

usamakenway

Pinned Loading

  1. Easy-LLM-Server Easy-LLM-Server Public

    Use open source models in your app using Api, and test it in Realtime using gradio.

    Python 5 1

  2. NuraStyle-Final_Year_Project NuraStyle-Final_Year_Project Public

    Style transferred model quantized for an android app for a final year project ( 2021 )

    Java

  3. oobabooga/textgen oobabooga/textgen Public

    The original local LLM interface. Text, vision, tool-calling, training. UI + API, 100% offline and private.

    Python 46.9k 6k

  4. prompt-generator_stable-diffusion_using_T5 prompt-generator_stable-diffusion_using_T5 Public

    Jupyter Notebook