High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.
☆212Oct 9, 2026Updated this week
Alternatives and similar repositories for pegaflow
Users that are interested in pegaflow are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 9 months ago
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆718Updated this week
- KV cache store for distributed LLM inference☆446Sep 16, 2026Updated 3 weeks ago
- High Performance KV Cache Store for LLM☆58May 20, 2026Updated 4 months ago
- Early-stage Rust drop-in alternative frontend for vLLM☆73May 22, 2026Updated 4 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A high-performance and light-weight router for vLLM large scale deployment☆460Updated this week
- A workload for deploying LLM inference services on Kubernetes☆302Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,204Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,293Updated this week
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆564Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,746Updated this week
- a high-performance, large-capacity, multi-tenant, data-persistent, strong data consistency based on raft, Redis-compatible elastic KV dat…☆58Updated this week
- ☆181Apr 23, 2026Updated 5 months ago
- ☆29Sep 24, 2026Updated 2 weeks ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- SiMM: Scalable in-Memory Middleware☆43Sep 24, 2026Updated 2 weeks ago
- mKernel: fast multi-node, multi-GPU fused kernels☆289Updated this week
- ☆362Updated this week
- ☆123Updated this week
- Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSi…☆265Updated this week
- Fast and memory-efficient exact attention☆23Jun 26, 2026Updated 3 months ago
- htop-like TUI for real-time RDMA network monitoring.☆113Oct 2, 2026Updated last week
- ☆97Sep 15, 2025Updated last year
- Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and i…☆182Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,985Updated this week
- PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]☆63Aug 17, 2026Updated last month
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,330Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,845Sep 24, 2026Updated 2 weeks ago
- ☆932Updated this week
- A lightweight, configurable, and real-time simulator designed to mimic the behavior of vLLM without the need for GPUs or running actual h…☆211Updated this week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆513Updated this week
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆536Nov 19, 2025Updated 10 months ago
- ☆137Nov 11, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Agent-friendly GPU profile-query CLI☆128Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,251Updated this week
- High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogen…☆414Updated this week
- Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.☆334Sep 9, 2026Updated last month
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆1,536Updated this week
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Updated this week
- Offline optimization of your disaggregated Dynamo graph☆457Sep 18, 2026Updated 3 weeks ago