arcusbuilds/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Repositories
arcusbuilds/GPUMD
Graphics Processing Units Molecular Dynamics
arcusbuilds/quadrants
High-performance multi-platform compiler for physics simulation
arcusbuilds/Halide
a language for fast, portable data-parallel computation
arcusbuilds/Cabana
Performance-portable library for particle-based simulations
arcusbuilds/Metal.jl
Metal programming in Julia
arcusbuilds/FlagGems
FlagGems is an operator library for large language models implemented in the Triton Language.
arcusbuilds/dynamo
A Datacenter Scale Distributed Inference Serving Framework
arcusbuilds/xgboost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
arcusbuilds/arcusbuilds.github.io
Personal site for open-source work and career progress
arcusbuilds/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
arcusbuilds/Megatron-LM
Ongoing research training transformer models at scale
arcusbuilds/SpargeAttn
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
arcusbuilds/DALI
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
arcusbuilds/Liger-Kernel
Efficient Triton Kernels for LLM Training
arcusbuilds/Trixi.jl
Trixi.jl: Adaptive high-order numerical simulations of conservation laws in Julia
arcusbuilds/comfy-kitchen
Fast kernel library for Diffusion inference with multiple compute backends.
arcusbuilds/tokamax
Tokamax: A GPU and TPU kernel library.
arcusbuilds/podman
Podman: A tool for managing OCI containers and pods.
arcusbuilds/flash-linear-attention
🚀 Efficient implementations for emerging model architectures
arcusbuilds/trl
Train transformer language models with reinforcement learning.
arcusbuilds/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
arcusbuilds/cilium
eBPF-based Networking, Security, and Observability
arcusbuilds/relion
Image-processing software for cryo-electron microscopy
arcusbuilds/circt
Circuit IR Compilers and Tools
arcusbuilds/cutile-rs
cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for passing tensors to asynchronously executed kernel functions.
arcusbuilds/wgpu
A cross-platform, safe, pure-Rust graphics API.
arcusbuilds/cccl
CUDA Core Compute Libraries
arcusbuilds/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
arcusbuilds/burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.