discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
uccl-project/uccl
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
History and source changes · Reports and owner responses · Compare
Similar
- flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
Why this match
topics cuda, gpu, moe; language differs: C++ → Cuda
- NVIDIA/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Why this match
topics cuda, gpu, nvidia
- NVIDIA/warp
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
Why this match
topics cuda, gpu, nvidia; language differs: C++ → Python
- kvcache-ai/Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Why this match
topics kvcache, llm, rdma
- NVIDIA/nvidia-docker
Build and run Docker containers leveraging NVIDIA GPUs
Why this match
topics cuda, gpu
- NVIDIA/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Why this match
topics cuda, moe; language differs: C++ → Python
- Syllo/nvtop
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
Why this match
topics amd, gpu, nvidia; language differs: C++ → C
- lupinemachines/lupine
LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
Why this match
topics cuda, gpu, networking