catid
Focus on erasure correction coding (ECC/FEC), cryptography, networking libraries, lossless image compression, Azure Kinect, XR, Large Language Models
Austin, TX
Pinned Repositories
cuda_float_compress
Python package for compressing floating-point PyTorch tensors
dora
Implementation of DoRA
fecal
FEC-AL : O(N^2) Fountain Code for Small Data
leopard
Leopard-RS : O(N Log N) MDS Reed-Solomon Block Erasure Code for Large Data
longhair
Longhair : O(N^2) Cauchy Reed-Solomon Block Erasure Code for Small Data
self-discover
Implementation of Google's SELF-DISCOVER
supercharger
Supercharge Open-Source AI Models
wirehair
Wirehair : O(N) Fountain Code for Large Data
WLANOptimizer
Single-header C library that fixes WiFi performance issues for online gaming and other low-latency real-time network traffic.
Zpng
Better lossless compression than PNG with a simpler algorithm
catid's Repositories
catid/self-discover
Implementation of Google's SELF-DISCOVER
catid/dora
Implementation of DoRA
catid/longhair
Longhair : O(N^2) Cauchy Reed-Solomon Block Erasure Code for Small Data
catid/cm256
Fast GF(256) Cauchy MDS Block Erasure Codec in C
catid/tonk
Tonk : Reliable UDP (rUDP) Network Library and Infinite Window Erasure Code
catid/bitnet_cpu
Experiments with BitNet inference on CPU
catid/oaillama3
Simple setup to self-host LLaMA3-70B model with an OpenAI API
catid/lllm
Latent Large Language Models
catid/dataloader
High-performance tokenized language data-loader for Python C++ extension
catid/cuda_float_compress
Python package for compressing floating-point PyTorch tensors
catid/AQLM
Fixes for AQLM
catid/chainlit-anthropic
Chainlit AI UI with Anthropic Backend
catid/cifar10deepspeed
Using DeepSpeed and Nvidia DALI to train various models to solve CIFAR-10
catid/quicsend
quicsend :: Super-fast Internet-ready file transfer right from Python
catid/textworld_llm_benchmark
TextWorld LLM Benchmark
catid/swe_agent_playground
swe_agent_playground
catid/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
catid/cuSZp
catid/exllamav2
Add repeat-layer feature to exllamav2
catid/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
catid/hgru2-pytorch
catid/InstantMesh
Fix for CUDA out of memory
catid/libdebayer
catid/mirage
A multi-level tensor algebra superoptimizer
catid/modded-nanogpt
NanoGPT (124M) quality in 2.67B tokens
catid/PruneMe
Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models
catid/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
catid/quiche
🥧 Savoury implementation of the QUIC transport protocol and HTTP/3
catid/quip-sharp
Fixes to get it working for LLaMA3
catid/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.