ai-dynamo / aiconfiguratorLinks
Offline optimization of your disaggregated Dynamo graph
☆168Updated this week
Alternatives and similar repositories for aiconfigurator
Users that are interested in aiconfigurator are comparing it to the libraries listed below
Sorting:
- Efficient and easy multi-instance LLM serving☆521Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆123Updated last month
- Stateful LLM Serving☆94Updated 10 months ago
- NVIDIA NCCL Tests for Distributed Training☆133Updated last week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆252Updated this week
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆90Updated last week
- GLake: optimizing GPU memory management and IO transmission.☆497Updated 10 months ago
- NVIDIA Inference Xfer Library (NIXL)☆844Updated this week
- Hooked CUDA-related dynamic libraries by using automated code generation tools.☆172Updated 2 years ago
- KV cache store for distributed LLM inference☆387Updated 2 months ago
- Systematic and comprehensive benchmarks for LLM systems.☆48Updated 2 months ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆122Updated 2 years ago
- A lightweight design for computation-communication overlap.☆213Updated last week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆360Updated this week
- DeepSeek-V3/R1 inference performance simulator☆177Updated 10 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- Fast and memory-efficient exact attention☆110Updated this week
- NCCL Profiling Kit☆150Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆66Updated last year
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆253Updated this week
- Perplexity GPU Kernels☆554Updated 2 months ago
- A low-latency & high-throughput serving engine for LLMs☆470Updated 2 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆457Updated 7 months ago
- GPU-scheduler-for-deep-learning☆210Updated 5 years ago
- ☆93Updated 9 months ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆760Updated 2 weeks ago
- An interference-aware scheduler for fine-grained GPU sharing☆159Updated 2 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- A tool for bandwidth measurements on NVIDIA GPUs.☆610Updated 9 months ago
- RDMA and SHARP plugins for nccl library☆221Updated 2 weeks ago