DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
☆617Oct 14, 2026Updated 2 weeks ago
Alternatives and similar repositories for DeepGEMM-Ascend
Users that are interested in DeepGEMM-Ascend 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 high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.☆278Sep 30, 2026Updated 3 weeks ago
- DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers☆520Sep 30, 2026Updated 3 weeks ago
- A lightweight library for xPU kernel JIT compilation☆429Oct 19, 2026Updated last week
- Clangd for Ascend for Code Lint & Code Completion☆34Sep 29, 2026Updated last month
- A kernel library written in tilelang☆2,012Oct 14, 2026Updated 2 weeks 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.
- ☆39Aug 4, 2026Updated 2 months ago
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,195Oct 12, 2026Updated 2 weeks ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,289Updated this week
- An internal component used by DeepSeek Harness☆19Oct 12, 2026Updated 2 weeks ago
- Ascend TileLang adapter☆419Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,805Updated this week
- Reference implementation and examples of the CuTe Layout representation and algebra.☆381Updated this week
- DeepInfer: High-performance, large-scale inference framework for DeepSeek models☆23,113Updated this week
- ☆133Updated this week
- 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.
- Mixture-of-experts (MoE) training megakernel for NVL72s☆634Oct 1, 2026Updated 3 weeks ago
- ☆2,572Oct 19, 2026Updated last week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆9,106Oct 20, 2026Updated last week
- high-performance linear attention kernel library built on TileLang☆738Oct 14, 2026Updated 2 weeks ago
- AgentENV (AENV) is a distributed platform for running agent environments at scale.☆3,693Updated this week
- ☆78Sep 30, 2026Updated 3 weeks ago
- Skills for writing tilelang and debugging with CUDA toolkits.☆146Updated this week
- Agent-friendly GPU profile-query CLI☆128Oct 4, 2026Updated 3 weeks ago
- TensorIR is a lightweight NVIDIA-owned MLIR compiler frontend for expressing tensor computations and lowering them to NVIDIA CUDA Tile IR…☆140Oct 15, 2026Updated 2 weeks ago
- 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 collection of megakernels for TPU☆171Oct 15, 2026Updated 2 weeks ago
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆13,194Oct 15, 2026Updated 2 weeks ago
- Open ML Compiler Foundation☆28Updated this week
- DeepEP: an efficient expert-parallel communication library☆10,369Oct 21, 2026Updated last week
- Distributed Compiler and Optimized Parallel Kernels☆1,573Sep 18, 2026Updated last month
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,446Oct 19, 2026Updated last week
- ☆32Jul 2, 2025Updated last year
- DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference. Includes the MICRO 2026 AE a…☆66Oct 5, 2026Updated 3 weeks ago
- An Open Compiler Harness for Agentic GPU Programming☆174Updated this week
- 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.
- TokenSpeed is a speed-of-light LLM inference engine.☆2,814Updated this week
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- Flash-GMM, a memory-efficient GPU kernel that unlocks GMM soft clustering at billion-scale☆25Sep 30, 2026Updated 3 weeks ago
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,250Jul 9, 2026Updated 3 months ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆312Oct 22, 2026Updated last week
- ☆53Oct 22, 2026Updated last week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,875Sep 24, 2026Updated last month