-
student
- USA
- narain1.github.io
- @narain13579
- https://narain1.netlify.app
Lists (3)
Sort Name ascending (A-Z)
Starred repositories
High performance self-hosted photo and video management solution.
No-GIL Python environment featuring NVIDIA Deep Learning libraries.
Code to easily try 30 (and growing) different image matching methods
Revitalizing Convolutional Network for Image Restoration
how to optimize some algorithm in cuda.
releasing everyone's SSN and the hacks used to acquire them
real time face swap and one-click video deepfake with only a single image
Helpful tools and examples for working with flex-attention
Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2
Explorations into some recent techniques surrounding speculative decoding
🎉 Modern CUDA Learn Notes with PyTorch: fp32, fp16, bf16, fp8/int8, flash_attn, sgemm, sgemv, warp/block reduce, dot, elementwise, softmax, layernorm, rmsnorm.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
AdalFlow: The library to build & auto-optimize any LLM tasks.
A curated list of practical financial machine learning tools and applications.
NanoGPT (124M) quality in 3.7B tokens
Open source real-time translation app for Android that runs locally
🌒 Shell command obfuscation to avoid detection systems
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
terrelln / dietgpu
Forked from facebookresearch/dietgpuGPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.
This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…