DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
☆639Oct 14, 2026Updated last month
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.☆296Nov 3, 2026Updated 2 weeks ago
- DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers☆550Sep 30, 2026Updated last month
- A lightweight library for xPU kernel JIT compilation☆471Nov 5, 2026Updated last week
- A kernel library written in tilelang☆2,077Oct 14, 2026Updated last month
- Clangd for Ascend for Code Lint & Code Completion☆38Sep 29, 2026Updated last month
- 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.
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,992Updated this week
- An internal component used by DeepSeek Harness☆24Oct 12, 2026Updated last month
- ☆41Nov 3, 2026Updated 2 weeks ago
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,214Oct 12, 2026Updated last month
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,297Updated this week
- Ascend TileLang adapter☆431Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆9,201Oct 20, 2026Updated 3 weeks ago
- DeepInfer: High-performance, large-scale inference framework for DeepSeek models☆26,157Nov 3, 2026Updated 2 weeks ago
- ☆330Nov 11, 2026Updated last week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆13,276Oct 27, 2026Updated 3 weeks ago
- ☆2,893Oct 19, 2026Updated 3 weeks ago
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,594Oct 19, 2026Updated 3 weeks ago
- Triton language and compiler for Huawei Ascend NPU☆216Updated this week
- ☆147Updated this week
- Reference implementation and examples of the CuTe Layout representation and algebra.☆397Nov 3, 2026Updated 2 weeks ago
- Mixture-of-experts (MoE) training megakernel for NVL72s☆646Oct 1, 2026Updated last month
- high-performance linear attention kernel library built on TileLang☆758Oct 30, 2026Updated 2 weeks ago
- DeepEP: an efficient expert-parallel communication library☆10,450Oct 21, 2026Updated 3 weeks ago
- 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.
- Skills for writing tilelang and debugging with CUDA toolkits.☆149Nov 11, 2026Updated last week
- Distributed Compiler and Optimized Parallel Kernels☆1,580Sep 18, 2026Updated 2 months ago
- High-performance LLM operator library built on TileLang.☆203Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,317Jul 9, 2026Updated 4 months ago
- High Performance LLM Inference Operator Library☆1,191Nov 10, 2026Updated last week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,904Sep 24, 2026Updated last month
- FlashInfer: Kernel Library for LLM Serving☆6,949Updated this week
- TensorIR is a lightweight NVIDIA-owned MLIR compiler frontend for expressing tensor computations and lowering them to NVIDIA CUDA Tile IR…☆141Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,930Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Agent-friendly GPU profile-query CLI☆131Oct 4, 2026Updated last month
- ☆32Jul 2, 2025Updated last year
- AgentENV (AENV) is a distributed platform for running agent environments at scale.☆3,754Updated this week
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆551Nov 19, 2025Updated 11 months ago
- A collection of megakernels for TPU☆188Oct 15, 2026Updated last month
- An Open Compiler Harness for Agentic GPU Programming☆209Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆47Updated this week
Are these results useful?