ai-dynamo / nixlLinks
NVIDIA Inference Xfer Library (NIXL)
☆536Updated this week
Alternatives and similar repositories for nixl
Users that are interested in nixl are comparing it to the libraries listed below
Sorting:
- Ultra and Unified CCL☆483Updated this week
- Efficient and easy multi-instance LLM serving☆468Updated this week
- KV cache store for distributed LLM inference☆311Updated 2 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆398Updated this week
- Perplexity GPU Kernels☆435Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆405Updated 2 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆669Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆407Updated 2 months ago
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆202Updated last week
- A tool for bandwidth measurements on NVIDIA GPUs.☆511Updated 4 months ago
- CUDA checkpoint and restore utility☆360Updated 6 months ago
- GLake: optimizing GPU memory management and IO transmission.☆473Updated 4 months ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆120Updated last year
- Zero Bubble Pipeline Parallelism☆418Updated 3 months ago
- Microsoft Collective Communication Library☆357Updated last year
- Materials for learning SGLang☆530Updated last month
- DeepSeek-V3/R1 inference performance simulator☆164Updated 4 months ago
- NCCL Profiling Kit☆141Updated last year
- ☆279Updated last week
- OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)☆226Updated this week
- Fast OS-level support for GPU checkpoint and restore☆228Updated last week
- A validation and profiling tool for AI infrastructure☆328Updated this week
- RDMA and SHARP plugins for nccl library☆200Updated 2 months ago
- A PyTorch Native LLM Training Framework☆861Updated last month
- Distributed Compiler based on Triton for Parallel Systems☆1,031Updated last week
- NVIDIA NCCL Tests for Distributed Training☆105Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆104Updated 3 months ago
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆561Updated this week
- A large-scale simulation framework for LLM inference☆423Updated 3 weeks ago
- High performance Transformer implementation in C++.☆129Updated 7 months ago