Accelerating MoE with IO and Tile-aware Optimizations
☆714Jun 15, 2026Updated this week
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:
- Distributed Compiler based on Triton for Parallel Systems☆1,459Apr 22, 2026Updated last month
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,489Updated this week
- A Quirky Assortment of CuTe Kernels☆1,017Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,791Updated this week
- Cute layout visualization☆40Jan 18, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆121May 19, 2025Updated last year
- Tile primitives for speedy kernels☆3,436Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,328Aug 28, 2025Updated 9 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,227Jun 11, 2026Updated last week
- ☆37Aug 7, 2025Updated 10 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆237Jun 8, 2026Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆190Apr 8, 2026Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,006Feb 5, 2026Updated 4 months 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…☆3,390Updated 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.
- Perplexity GPU Kernels☆586Nov 7, 2025Updated 7 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆393Jul 10, 2025Updated 11 months ago
- A lightweight design for computation-communication overlap.☆237Jan 20, 2026Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,086Sep 4, 2024Updated last year
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆885Updated this week
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆109Dec 2, 2025Updated 6 months ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,402Jun 8, 2026Updated last week
- ☆137Jun 6, 2025Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,305Updated 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.
- A sparse attention kernel supporting mix sparse patterns☆525Jan 18, 2026Updated 5 months ago
- From Minimal GEMM to Everything☆220Jun 8, 2026Updated last week
- LM engine is a library for pretraining/finetuning LLMs☆176Jun 12, 2026Updated last week
- a size profiler for cuda binary☆70Jan 15, 2026Updated 5 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆548Jun 11, 2026Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆7,370Jun 4, 2026Updated 2 weeks ago
- incubator repo for CUDA-TileIR backend☆140Jun 12, 2026Updated last week
- ☆23Aug 20, 2025Updated 9 months ago
- Nex Venus Communication Library☆76Nov 17, 2025Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆181Updated this week
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆105Apr 7, 2026Updated 2 months ago
- ☆249Nov 19, 2025Updated 6 months ago
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆194Apr 21, 2026Updated last month
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,425Jan 17, 2026Updated 5 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆266May 5, 2026Updated last month