PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.
☆25Jan 7, 2026Updated 10 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 3 months ago
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆221Updated this week
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆14Oct 30, 2026Updated 2 weeks ago
- High Performance KV Cache Store for LLM☆59May 20, 2026Updated 5 months ago
- TiSpace manages VMs in K8s for developers☆14Nov 16, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A user level library for applications to transparently use Intel DSA.☆46Oct 31, 2026Updated 2 weeks ago
- 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
- ☆11Nov 11, 2025Updated last year
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆746Updated this week
- ☆28Oct 4, 2026Updated last month
- A Rust RDMA library.☆13Oct 16, 2026Updated last month
- ☆28Updated this week
- Code Implementation for OSCAR 2026 Workshop: Toward Sustainable GPU Modeling: Autonomous Micro-benchmarking with LLM Agents☆17Jun 28, 2026Updated 4 months ago
- Examples of usage for Mellanox HW offloads☆17Jan 18, 2022Updated 4 years ago
- 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.
- Skyloft: A General High-Efficient Scheduling Framework in User Space (SOSP 2024)☆40Sep 15, 2024Updated 2 years ago
- The Intelligent Inference Scheduler for Large-scale Inference Services.☆72Feb 12, 2026Updated 9 months ago
- ☆18Updated this week
- High-performance Rust benchmark client for vLLM serving endpoints.☆53Aug 3, 2026Updated 3 months ago
- LLM Kernel Library for Rust☆32Oct 30, 2026Updated 2 weeks ago
- Contain some materials about CXL.☆20Feb 29, 2024Updated 2 years ago
- Production-ready MoE load balancing via real-time expert replication☆265Oct 15, 2026Updated last month
- User space Block device access API☆14Aug 25, 2026Updated 2 months ago
- [AFK] Hardware router in Chisel (THU Network Joint Lab 2020)☆14Oct 8, 2020Updated 6 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆20Jul 11, 2024Updated 2 years ago
- High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU [SIGMOD'26]☆33Oct 20, 2026Updated 3 weeks ago
- Uni-Agent is a framework for training long-horizon agents.☆26Sep 21, 2026Updated last month
- ☆12Apr 5, 2024Updated 2 years ago
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2026☆50Sep 28, 2026Updated last month
- ☆29Updated this week
- Take your first step in writing a compiler. Implemented in Rust.☆16Apr 17, 2023Updated 3 years ago
- a size profiler for cuda binary☆74Oct 3, 2026Updated last month
- Ensō is a high-performance streaming interface for NIC-application communication.☆86Apr 11, 2026Updated 7 months ago
- 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.
- A modular framework for evaluating disk-based vector search, enabling controlled ablations and end-to-end comparisons across diverse stor…☆14Oct 15, 2026Updated last month
- ☆19Mar 11, 2025Updated last year
- 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 2 months ago
- An agent for CUDA compute-communication kernel co-design☆37May 7, 2026Updated 6 months ago
- A scalable RAID system to aggregate performance and capacity of the next-generation storage.☆17Jan 3, 2024Updated 2 years ago
- What if everything is a io_uring?☆17Nov 10, 2022Updated 4 years ago
- Tutti is a GPU-centric KV Cache Store to make SSD work as DRAM.☆73Nov 4, 2026Updated 2 weeks ago
Are these results useful?