Aggressive decode optimizations for Qwen3-0.6B on RTX 5090
☆53Feb 25, 2026Updated 4 months ago
Alternatives and similar repositories for qwen_megakernel
Users that are interested in qwen_megakernel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆116Feb 10, 2026Updated 5 months ago
- Region-level profiling for CUDA kernels with trace, NVBit, CUPTI, NSys, and an interactive Explorer.☆121Apr 17, 2026Updated 3 months ago
- Super fast serving stack for LLM on Windows/Linux/Macos☆17Dec 17, 2025Updated 7 months ago
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆16Dec 31, 2025Updated 6 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆21Jul 3, 2024Updated 2 years 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.
- High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.☆31Apr 5, 2026Updated 3 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆251Jun 21, 2026Updated 3 weeks ago
- ☆18Dec 2, 2024Updated last year
- Implementation of a Light Recurrent Unit in Pytorch☆50Oct 6, 2024Updated last year
- mHC kernels implemented in CUDA☆264Mar 9, 2026Updated 4 months ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆110Dec 17, 2025Updated 7 months ago
- Low overhead tracing library and trace visualizer for pipelined CUDA kernels☆137Updated this week
- ☆19Jan 4, 2024Updated 2 years ago
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆148Jun 10, 2026Updated last month
- 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.
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 3 months ago
- ☆158Updated this week
- ☆11Mar 9, 2022Updated 4 years ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆115Jun 28, 2025Updated last year
- ☆11Oct 13, 2023Updated 2 years ago
- Reverse engineered the Apple Neural Engine, with working Python and Objective C samples☆34Feb 1, 2026Updated 5 months ago
- [IPDPS 2024] Adaptive neighbor sampling for temporal GNN☆16Feb 17, 2025Updated last year
- Github mirror of trition-lang/triton repo.☆178Updated this week
- ☆46Oct 23, 2025Updated 8 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- 用pytorch训练18层残差神经网络，用pyqt设计界面☆12Jun 23, 2020Updated 6 years ago
- ☆12Mar 16, 2022Updated 4 years ago
- Next Generation Experimental Tracking for Machine Learning Operations☆17Updated this week
- My learning notes for ML&SYS.☆13Mar 27, 2026Updated 3 months ago
- An unbounded n-gram language model on Tiny Shakespeare☆22Jan 21, 2026Updated 5 months ago
- ☆19Mar 4, 2025Updated last year
- 存放一些 CUDA 编程相关的博客文件。☆22Oct 16, 2025Updated 9 months ago
- A Scheduler for Batched LLM Inference☆19Oct 5, 2025Updated 9 months ago
- A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.☆231Jun 29, 2026Updated 3 weeks ago
- 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.
- A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch☆367Jul 9, 2026Updated last week
- A Quirky Assortment of CuTe Kernels☆1,060Updated this week
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆24Jan 30, 2026Updated 5 months ago
- Optimize GEMM with tensorcore step by step☆40Dec 17, 2023Updated 2 years ago
- We bring the spirit of nanogpt-speedrun into the omni-modal world☆15Jan 31, 2026Updated 5 months ago
- Composable and Embeddable Communication Runtime for Distributed AI Services☆102Jun 5, 2026Updated last month
- ☆54Updated this week