NVIDIA Inference Xfer Library (NIXL)
☆1,304Oct 14, 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☆8,278Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,794Updated this week
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 11 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,618Updated this week
- KV cache store for distributed LLM inference☆446Sep 16, 2026Updated 3 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,540Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,373Aug 28, 2025Updated last year
- Distributed Compiler and Optimized Parallel Kernels☆1,566Sep 18, 2026Updated 3 weeks ago
- ☆389Jan 28, 2026Updated 8 months ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,016Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆562Updated this week
- Achieve state of the art inference performance with modern accelerators on Kubernetes☆4,819Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆597Oct 3, 2026Updated last week
- ☆369Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- torchcomms: a modern PyTorch communications API☆401Updated this week
- Offline optimization of your disaggregated Dynamo graph☆459Sep 18, 2026Updated 3 weeks ago
- Efficient and easy multi-instance LLM serving☆561Mar 12, 2026Updated 7 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆297Updated this week
- 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…☆183Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆842Apr 6, 2025Updated last year
- A lightweight design for computation-communication overlap.☆249Jan 20, 2026Updated 8 months ago
- Optimized primitives for collective multi-GPU communication☆5,164Updated this week
- Perplexity open source garden for inference technology☆943Sep 2, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆275Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,552Updated this week
- Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)☆1,726Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,861Sep 24, 2026Updated 2 weeks ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆206Feb 11, 2026Updated 8 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,596Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆37,132Updated this week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆515Updated this week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆121Dec 17, 2025Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- TokenSpeed is a speed-of-light LLM inference engine.☆2,246Updated this week
- Modular RDMA Interface☆187Updated this week
- A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology☆1,424Sep 15, 2026Updated 3 weeks ago
- DeepEP: an efficient expert-parallel communication library☆10,280Sep 30, 2026Updated 2 weeks ago
- Tile primitives for speedy kernels☆3,749Sep 12, 2026Updated last month
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆2,670Updated this week
- Materials for learning SGLang☆898Jan 5, 2026Updated 9 months ago