This is my master's diploma work repository

No description provided.

No description provided.

Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performance.

A Datacenter Scale Distributed Inference Serving Framework

SGLang is a fast serving framework for large language models and vision language models.

Collective communications library with various primitives for multi-machine training.

Unified Collective Communication Library

Optimized primitives for collective multi-GPU communication

RDMA and SHARP plugins for nccl library

NCCL Tests

RDMA library for mapping associate netdevice and character devices

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group):

Test Repository ;)

No description provided.

No description provided.

Python bindings for UCX

A lightweight parameter server interface

No description provided.

Linux Cross-Memory Attach

Information about many aspects of high-performance computing. Wiki content moved to ~/docs.

Open MPI web site

No description provided.

Open Fabric Interfaces

This is a plugin which lets EC2 developers use libfabric as network provider while running NCCL applications.

Mellanox Vendor Tests

Google Test

Master course on Agile Development

No description provided.