ai-dynamo / nixlLinks
NVIDIA Inference Xfer Library (NIXL)
☆352Updated this week
Alternatives and similar repositories for nixl
Users that are interested in nixl are comparing it to the libraries listed below
Sorting:
- Efficient and easy multi-instance LLM serving☆420Updated this week
- Perplexity GPU Kernels☆318Updated last week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆360Updated this week
- ☆49Updated 2 months ago
- KV cache store for distributed LLM inference☆250Updated this week
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆164Updated last week
- A low-latency & high-throughput serving engine for LLMs☆368Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆378Updated last month
- Microsoft Collective Communication Library☆346Updated last year
- Zero Bubble Pipeline Parallelism☆395Updated 3 weeks ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆116Updated last year
- NCCL Profiling Kit☆134Updated 10 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆601Updated last month
- DeepSeek-V3/R1 inference performance simulator☆129Updated 2 months ago
- Distributed Triton for Parallel Systems☆765Updated this week
- NVIDIA NCCL Tests for Distributed Training☆91Updated last week
- A tool for bandwidth measurements on NVIDIA GPUs.☆430Updated last month
- RDMA and SHARP plugins for nccl library☆193Updated last month
- A library to analyze PyTorch traces.☆379Updated this week
- CUDA checkpoint and restore utility☆339Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆80Updated last week
- High performance Transformer implementation in C++.☆123Updated 4 months ago
- A lightweight design for computation-communication overlap.☆131Updated 3 weeks ago
- This is a plugin which lets EC2 developers use libfabric as network provider while running NCCL applications.☆172Updated last week
- Hooked CUDA-related dynamic libraries by using automated code generation tools.☆156Updated last year
- Microsoft Collective Communication Library☆65Updated 6 months ago
- ☆83Updated 5 months ago
- PyTorch distributed training acceleration framework☆49Updated 3 months ago
- Synthesizer for optimal collective communication algorithms☆106Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆239Updated last week