Perplexity open source garden for inference technology
☆927Sep 2, 2026Updated 3 weeks 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☆608Nov 7, 2025Updated 10 months ago
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,529Sep 20, 2026Updated last week
- torchcomms: a modern PyTorch communications API☆398Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,274Updated this week
- ☆388Jan 28, 2026Updated 7 months ago
- 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.
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆118Dec 17, 2025Updated 9 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆590Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,551Sep 18, 2026Updated last week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆558Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,366Aug 28, 2025Updated last year
- mKernel: fast multi-node, multi-GPU fused kernels☆281Sep 20, 2026Updated last week
- A lightweight design for computation-communication overlap.☆248Jan 20, 2026Updated 8 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,005Sep 15, 2026Updated last week
- Distributed MoE in a Single Kernel [NeurIPS '25]☆291May 5, 2026Updated 4 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.
- FlashInfer: Kernel Library for LLM Serving☆6,506Updated this week
- A Quirky Assortment of CuTe Kernels☆1,156Sep 17, 2026Updated last week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆204Feb 11, 2026Updated 7 months ago
- Nex Venus Communication Library☆77Nov 17, 2025Updated 10 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,176Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆771Aug 29, 2026Updated 3 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,664Updated this week
- Tile primitives for speedy kernels☆3,729Sep 12, 2026Updated 2 weeks ago
- Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming☆818Updated this week
- 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 size profiler for cuda binary☆71Jan 15, 2026Updated 8 months ago
- Modular RDMA Interface☆181Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,001Updated this week
- Venus Collective Communication Library, supported by SII and Infrawaves.☆152Sep 3, 2026Updated 3 weeks ago
- A Datacenter Scale Distributed Inference Serving Framework☆8,163Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,486Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,262Sep 1, 2026Updated 3 weeks ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,811Updated this week
- 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.
- KV cache store for distributed LLM inference☆444Sep 16, 2026Updated last week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,517Updated this week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆552Sep 20, 2026Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,556Updated this week
- PyTorch Single Controller☆1,078Updated this week
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆127Mar 7, 2026Updated 6 months ago
- Accepted to MLSys 2026☆96Apr 19, 2026Updated 5 months ago