Perplexity open source garden for inference technology
☆390Dec 25, 2025Updated 3 months ago
Alternatives and similar repositories for pplx-garden
Users that are interested in pplx-garden are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Perplexity GPU Kernels☆565Nov 7, 2025Updated 5 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆95Apr 6, 2026Updated last week
- Nex Venus Communication Library☆73Nov 17, 2025Updated 4 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆98Apr 7, 2026Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆970Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Open ABI and FFI for Machine Learning Systems☆375Updated this week
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 2 months ago
- ☆15Dec 13, 2024Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆177Feb 11, 2026Updated 2 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆498Updated this week
- A lightweight design for computation-communication overlap.☆226Jan 20, 2026Updated 2 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,403Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,372Updated this week
- Building the Virtuous Cycle for AI-driven LLM Systems☆217Updated this week
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆15Apr 20, 2022Updated 3 years ago
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,280Updated this week
- KV cache store for distributed LLM inference☆405Nov 13, 2025Updated 5 months ago
- ☆38Aug 7, 2025Updated 8 months ago
- Open source version of DOCA GPUNetIO and DOCA Verbs libraries (limited features) to enable GDAKI technology on RDMA (IB and RoCE)☆39Apr 9, 2026Updated last week
- ☆360Jan 28, 2026Updated 2 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆6,527Updated this week
- DeepSeek-V3/R1 inference performance simulator☆193Mar 27, 2025Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆98Dec 2, 2025Updated 4 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Aug 9, 2025Updated 8 months ago
- Venus Collective Communication Library, supported by SII and Infrawaves.☆142Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,286Aug 28, 2025Updated 7 months ago
- Fast OS-level support for GPU checkpoint and restore☆280Sep 28, 2025Updated 6 months ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆80Jul 25, 2023Updated 2 years ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆245Apr 6, 2026Updated last week
- Thunder Research Group's Collective Communication Library☆51Jul 8, 2025Updated 9 months ago
- ☆13Nov 21, 2024Updated last year
- An experimental communicating attention kernel based on DeepEP.☆35Jul 29, 2025Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Ths is a fast RDMA abstraction layer that works both in the kernel and user-space.☆59Nov 12, 2024Updated last year
- pytorch ucc plugin☆23Jul 8, 2021Updated 4 years ago
- Efficient and easy multi-instance LLM serving☆543Mar 12, 2026Updated last month
- ☆38Jul 19, 2025Updated 8 months ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆111Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆506Apr 9, 2026Updated last week
- NCCL Profiling Kit☆152Jul 1, 2024Updated last year