ai-dynamo / aiperfLinks
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
☆106Updated last week
Alternatives and similar repositories for aiperf
Users that are interested in aiperf are comparing it to the libraries listed below
Sorting:
- NVIDIA Inference Xfer Library (NIXL)☆844Updated last week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆260Updated this week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆365Updated this week
- Perplexity GPU Kernels☆554Updated 2 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆379Updated last week
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆253Updated last week
- Offline optimization of your disaggregated Dynamo graph☆168Updated last week
- A low-latency & high-throughput serving engine for LLMs☆470Updated 3 weeks ago
- torchcomms: a modern PyTorch communications API☆323Updated this week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆760Updated 3 weeks ago
- Perplexity open source garden for inference technology☆350Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆457Updated 8 months ago
- ☆133Updated this week
- Efficient and easy multi-instance LLM serving☆523Updated 4 months ago
- NVIDIA NCCL Tests for Distributed Training☆133Updated this week
- CUDA checkpoint and restore utility☆406Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆85Updated this week
- KV cache store for distributed LLM inference☆389Updated 2 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆459Updated last month
- ☆61Updated last year
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆455Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆205Updated last week
- LLM Serving Performance Evaluation Harness☆83Updated 11 months ago
- ☆71Updated 11 months ago
- QuickReduce is a performant all-reduce library designed for AMD ROCm that supports inline compression.☆36Updated 5 months ago
- A high-performance and light-weight router for vLLM large scale deployment☆95Updated last week
- Microsoft Collective Communication Library☆66Updated last year
- ☆83Updated 3 months ago
- The driver for LMCache core to run in vLLM☆60Updated 11 months ago
- Stateful LLM Serving☆95Updated 10 months ago