sgl-project / omeLinks
OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)
☆245Updated last week
Alternatives and similar repositories for ome
Users that are interested in ome are comparing it to the libraries listed below
Sorting:
- GPUd automates monitoring, diagnostics, and issue identification for GPUs☆415Updated this week
- Efficient and easy multi-instance LLM serving☆473Updated last week
- KV cache store for distributed LLM inference☆314Updated 2 months ago
- NVIDIA Inference Xfer Library (NIXL)☆569Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆195Updated last week
- NVIDIA NCCL Tests for Distributed Training☆107Updated last week
- A light weight vLLM simulator, for mocking out replicas.☆35Updated last week
- CUDA checkpoint and restore utility☆365Updated 7 months ago
- The driver for LMCache core to run in vLLM☆47Updated 6 months ago
- Distributed KV cache coordinator☆62Updated last week
- Perplexity GPU Kernels☆449Updated 3 weeks ago
- ☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!☆242Updated this week
- ☆314Updated last year
- Materials for learning SGLang☆549Updated last week
- A low-latency & high-throughput serving engine for LLMs☆408Updated 3 months ago
- Ultra and Unified CCL☆511Updated this week
- Common recipes to run vLLM☆110Updated last week
- GLake: optimizing GPU memory management and IO transmission.☆477Updated 5 months ago
- Automatic tuning for ML model deployment on Kubernetes☆80Updated 9 months ago
- Cloud Native Benchmarking of Foundation Models☆41Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆675Updated 4 months ago
- ☆31Updated 4 months ago
- Serverless LLM Serving for Everyone.☆522Updated this week
- LeaderWorkerSet: An API for deploying a group of pods as a unit of replication☆553Updated this week
- Stateful LLM Serving☆81Updated 5 months ago
- A tool to detect infrastructure issues on cloud native AI systems☆47Updated last month
- Fast OS-level support for GPU checkpoint and restore☆232Updated 2 weeks ago
- ☆58Updated 11 months ago
- ☆238Updated this week
- 🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.☆32Updated 2 weeks ago