Skip to content
View Dhruvdesai793's full-sized avatar
💭
Grinding
💭
Grinding
27 followers · 12 following

Achievements

Achievement: YOLOAchievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Pull SharkAchievement: Quickdraw

Block or report Dhruvdesai793

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.

Content in all repositories owned by your account will be closed.
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
Dhruvdesai793/README.md

DHRUV DESAI

Xploring


Current Path

Deep Learning
      │
      ▼
Transformers
      │
      ▼
PyTorch Internals
      │
      ▼
CUDA
      │
      ▼
Triton
      │
      ▼
Compiler Optimizations
      │
      ▼
ML Infrastructure

Focus

Learning:
  - Convolutional Neural Networks

Building:
  - Deep Learning implementations

Reading:
  - Dive into Deep Learning

Next:
  - Transformers

Exploring

FlashAttention
torch.compile()
Torch Dispatcher
Tensor Layouts
Kernel Fusion
Triton

Building

Tensor Operations
Autograd
Neural Network Modules
Optimizers
CNNs
Transformers

Stack

Languages
Deep Learning
Backend
Frontend
Systems

Progress

2026.07

✓ Tensor Fundamentals
✓ Tensor Storage & Strides
✓ Memory Layout
✓ Broadcasting
✓ Autograd
✓ Convolutional Neural Networks: LeNet, ResNeXt , DenseNet
→ RNN
→ Transformers
→ RL

Pinned Loading

  1. UNet-CamVid-Segmentation UNet-CamVid-Segmentation Public

    Semantic segmentation from scratch using U-Net, PyTorch, and the CamVid dataset.

    Python 1

  2. Tensorx.h Tensorx.h Public

    A C lang implementation of Tensors, autograd on cpu and cuda backend.

    C 1

  3. Build-Redis Build-Redis Public

    TypeScript 2

  4. cnn-papers-exp cnn-papers-exp Public

    This repo is made to record my experiments on cnn paper implementation that were built by me from scratch.

    Python 2