Accelerating MoE with IO and Tile-aware Optimizations
☆771Aug 29, 2026Updated 3 weeks ago
Alternatives and similar repositories for sonic-moe
Users that are interested in sonic-moe 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 Quirky Assortment of CuTe Kernels☆1,157Sep 17, 2026Updated last week
- Distributed Compiler and Optimized Parallel Kernels☆1,552Sep 18, 2026Updated last week
- mKernel: fast multi-node, multi-GPU fused kernels☆282Sep 20, 2026Updated last week
- Perplexity GPU Kernels☆609Nov 7, 2025Updated 10 months ago
- Tile primitives for speedy kernels☆3,730Sep 12, 2026Updated 2 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,367Aug 28, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆946Updated this week
- ☆255Nov 19, 2025Updated 10 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆291May 5, 2026Updated 4 months ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆953Updated this week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆553Sep 20, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,510Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,487Updated this week
- DeeperGEMM: crazy optimized version☆85May 5, 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.
- Kernels, of the mega variety :)☆835May 26, 2026Updated 4 months ago
- NVIDIA cuTile learn☆167Dec 9, 2025Updated 9 months ago
- Unified tracing profiler and visualizer, one timeline from CPU to GPU/HES to in-kernel zones☆147Updated this week
- Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming☆818Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,795Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,263Sep 1, 2026Updated 3 weeks ago
- High-performance LLM operator library built on TileLang.☆190Updated this week
- ☆171Dec 27, 2024Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,813Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,517Updated this week
- ☆32Jul 2, 2025Updated last year
- A kernel library written in tilelang☆1,777Apr 23, 2026Updated 5 months ago
- a size profiler for cuda binary☆71Jan 15, 2026Updated 8 months ago
- ☆469Aug 26, 2026Updated last month
- High Performance LLM Inference Operator Library☆1,168Sep 7, 2026Updated 3 weeks ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,555Updated this week
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆495Sep 17, 2026Updated last week
- Compact and Agent-Native MoE Training System☆353Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- PyTorch bindings for CUTLASS grouped GEMM.☆155May 29, 2025Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 8 months ago
- high-performance linear attention kernel library built on TileLang☆710Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,875Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆205Feb 11, 2026Updated 7 months ago
- A lightweight design for computation-communication overlap.☆248Jan 20, 2026Updated 8 months ago
- Tile-based language built for AI computation across all scales☆192Aug 25, 2026Updated last month