NVIDIA Inference Xfer Library (NIXL)
☆1,356Nov 2, 2026Updated this week
Alternatives and similar repositories for nixl
Users that are interested in nixl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Datacenter Scale Distributed Inference Serving Framework☆8,425Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,953Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,840Updated this week
- Perplexity GPU Kernels☆614Nov 7, 2025Updated 11 months ago
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,561Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- KV cache store for distributed LLM inference☆451Sep 16, 2026Updated last month
- Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)☆1,738Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,375Aug 28, 2025Updated last year
- Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and i…☆198Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,576Sep 18, 2026Updated last month
- Optimized primitives for collective multi-GPU communication☆5,202Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,253Updated this week
- A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology☆1,429Sep 15, 2026Updated last month
- ☆391Jan 28, 2026Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- State of the art inference performance with modern accelerators on Kubernetes☆5,126Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆569Updated this week
- DeepEP: an efficient expert-parallel communication library☆10,403Oct 21, 2026Updated 2 weeks ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆602Oct 28, 2026Updated last week
- Offline optimization of your disaggregated Dynamo graph☆463Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,884Sep 24, 2026Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆846Apr 6, 2025Updated last year
- ☆379Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆306Oct 17, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆286Updated this week
- (deprecated) torchcomms: a modern PyTorch communications API☆403Updated this week
- Efficient and easy multi-instance LLM serving☆560Mar 12, 2026Updated 7 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,841Updated this week
- Modular RDMA Interface☆191Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,342Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,587Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,890Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,993Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Open Source AI Accelerator Research Platform Standard / 开源推理研究平台☆1,956Updated this week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆122Dec 17, 2025Updated 10 months ago
- AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solu…☆844Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆526Aug 24, 2026Updated 2 months ago
- Tile primitives for speedy kernels☆3,790Sep 12, 2026Updated last month
- A lightweight design for computation-communication overlap.☆252Jan 20, 2026Updated 9 months ago
- NCCL Tests☆1,686Oct 5, 2026Updated 3 weeks ago