A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Team.
☆35Aug 6, 2026Updated 3 months ago
Alternatives and similar repositories for UCL-MPComm
Users that are interested in UCL-MPComm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆17Updated this week
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 10 months ago
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated last year
- ☆11Oct 29, 2026Updated last week
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆17May 25, 2026Updated 5 months 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.
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆123Dec 17, 2025Updated 10 months ago
- ☆14Nov 1, 2026Updated last week
- ☆46Oct 15, 2025Updated last year
- ☆16Mar 15, 2026Updated 7 months ago
- Tutti is a GPU-centric KV Cache Store to make SSD work as DRAM.☆70Updated this week
- Models Take Notes at Prefill: KV Cache Can Be Editable and Composable (arXiv:2606.17107) — paper, code, results, and interactive companio…☆16Updated this week
- ☆37Aug 7, 2025Updated last year
- 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.
- ☆121Updated this week
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆14Oct 30, 2026Updated last week
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2026☆50Sep 28, 2026Updated last month
- ☆19Jun 3, 2023Updated 3 years ago
- ☆18Jun 4, 2026Updated 5 months ago
- ☆15Jul 18, 2023Updated 3 years ago
- Network-Accelerated Distributed Deep Learning☆10Sep 13, 2021Updated 5 years ago
- ☆382Updated this week
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆127Mar 7, 2026Updated 8 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆11Nov 11, 2025Updated 11 months ago
- High-performance RDMA for Python and PyTorch (ibverbs, efa, NVMe-oF)☆14Sep 2, 2026Updated 2 months ago
- ☆13May 21, 2026Updated 5 months ago
- ☆10Jul 31, 2025Updated last year
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆19Jun 17, 2026Updated 4 months ago
- High Performance KV Cache Store for LLM☆59May 20, 2026Updated 5 months ago
- ☆34Jul 13, 2026Updated 3 months ago
- a size profiler for cuda binary☆74Oct 3, 2026Updated last month
- ☆15Sep 22, 2025Updated 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.
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- waverless: A serverless framework written by rust with WASM, CRIU, FunctionGraph, Integrated Storage☆13May 22, 2025Updated last year
- ☆12Oct 23, 2025Updated last year
- Efficient GPU communication over multiple NICs.☆31Nov 20, 2025Updated 11 months 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
- Code Implementation for OSCAR 2026 Workshop: Toward Sustainable GPU Modeling: Autonomous Micro-benchmarking with LLM Agents☆16Jun 28, 2026Updated 4 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆119Oct 28, 2026Updated last week
Are these results useful?