PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.
☆25Jan 7, 2026Updated 9 months ago
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:
- A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Te…☆35Aug 6, 2026Updated 2 months ago
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆13Oct 20, 2026Updated last week
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆218Updated this week
- High Performance KV Cache Store for LLM☆59May 20, 2026Updated 5 months ago
- TiSpace manages VMs in K8s for developers☆14Nov 16, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A user level library for applications to transparently use Intel DSA.☆46Updated this week
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆24Oct 20, 2024Updated 2 years ago
- ☆28Oct 4, 2026Updated 3 weeks ago
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆726Updated this week
- ☆11Nov 11, 2025Updated 11 months ago
- A Rust RDMA library.☆13Oct 16, 2026Updated last week
- An agent skill that turns a system, module, or unbuilt feature into a single-file HTML swimlane brief for readers outside the team — with…☆19Aug 30, 2026Updated last month
- ☆28Updated this week
- Uni-Agent is a framework for training long-horizon agents.☆24Sep 21, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Reverse-engineered instruction set architecture database for NVIDIA SM120 (Blackwell) GPUs.☆25Updated this week
- Skyloft: A General High-Efficient Scheduling Framework in User Space (SOSP 2024)☆39Sep 15, 2024Updated 2 years ago
- Examples of usage for Mellanox HW offloads☆17Jan 18, 2022Updated 4 years ago
- ☆12Apr 5, 2024Updated 2 years ago
- The Intelligent Inference Scheduler for Large-scale Inference Services.☆72Feb 12, 2026Updated 8 months ago
- User space Block device access API☆14Aug 25, 2026Updated 2 months ago
- High-performance Rust benchmark client for vLLM serving endpoints.☆52Aug 3, 2026Updated 2 months ago
- Production-ready MoE load balancing via real-time expert replication☆258Oct 15, 2026Updated 2 weeks ago
- Tutti is a GPU-centric KV Cache Store to make SSD work as DRAM.☆67Oct 14, 2026Updated 2 weeks ago
- 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.
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2026☆48Sep 28, 2026Updated last month
- LLM Kernel Library for Rust☆32Updated this week
- Contain some materials about CXL.☆20Feb 29, 2024Updated 2 years ago
- C++17 分布式 KV 存储 / distributed key-value store · Raft · shard routing · replica resize · recovery☆19Updated this week
- A scalable RAID system to aggregate performance and capacity of the next-generation storage.☆17Jan 3, 2024Updated 2 years ago
- [AFK] Hardware router in Chisel (THU Network Joint Lab 2020)☆14Oct 8, 2020Updated 6 years ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆103Jan 16, 2026Updated 9 months ago
- ☆20Jul 11, 2024Updated 2 years ago
- a size profiler for cuda binary☆74Oct 3, 2026Updated 3 weeks ago
- 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.
- Take your first step in writing a compiler. Implemented in Rust.☆16Apr 17, 2023Updated 3 years ago
- An agent for CUDA compute-communication kernel co-design☆37May 7, 2026Updated 5 months ago
- What if everything is a io_uring?☆17Nov 10, 2022Updated 3 years ago
- Clangd for Ascend for Code Lint & Code Completion☆34Sep 29, 2026Updated last month
- A unified workflow orchestration and distributed KV cache sharing framework for multimodal inference.☆38Sep 4, 2026Updated last month
- [FAST'25] ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover.☆20Feb 11, 2025Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆119Aug 4, 2026Updated 2 months ago