ai-dynamo / nixlLinks
NVIDIA Inference Xfer Library (NIXL)
☆844Updated last 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☆523Updated 4 months ago
- Perplexity GPU Kernels☆554Updated 2 months ago
- KV cache store for distributed LLM inference☆389Updated 2 months ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆760Updated 3 weeks ago
- Disaggregated serving system for Large Language Models (LLMs).☆772Updated 9 months ago
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆253Updated last week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆455Updated this week
- A low-latency & high-throughput serving engine for LLMs☆470Updated 3 weeks ago
- Materials for learning SGLang☆728Updated 3 weeks ago
- Offline optimization of your disaggregated Dynamo graph☆168Updated last week
- GLake: optimizing GPU memory management and IO transmission.☆497Updated 10 months ago
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆365Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆457Updated 8 months ago
- CUDA checkpoint and restore utility☆406Updated 4 months ago
- Perplexity open source garden for inference technology☆350Updated last month
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆260Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,322Updated last month
- torchcomms: a modern PyTorch communications API☆323Updated this week
- NVIDIA NCCL Tests for Distributed Training☆133Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆459Updated last month
- A tool for bandwidth measurements on NVIDIA GPUs.☆610Updated 9 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆659Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,235Updated 5 months ago
- Zero Bubble Pipeline Parallelism☆449Updated 8 months ago
- AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solu…☆106Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆943Updated 3 months ago
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆654Updated last month
- ☆342Updated this week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆923Updated 2 months ago
- A high-performance and light-weight router for vLLM large scale deployment☆95Updated last week