Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)
☆113Feb 10, 2026Updated 4 months ago
Alternatives and similar repositories for MegaQwen
Users that are interested in MegaQwen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- EleutherAI ML Performance reading group repository (slides, meeting recordings, annotated papers)☆35Mar 20, 2026Updated 3 months ago
- ☆12Mar 16, 2022Updated 4 years ago
- ☆28Jun 25, 2026Updated last week
- Optimize GEMM with tensorcore step by step☆40Dec 17, 2023Updated 2 years ago
- PyTorch Code for the Paper: "Exploiting Uncertainty of Loss Landscape for Stochastic Optimization [Bhaskara et al. (2019)]☆16Apr 30, 2026Updated 2 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.
- [ICLR2026] The first W4A4KV4 quantized + 50% sparse LLMs!☆33Jan 26, 2026Updated 5 months ago
- ☆14Aug 28, 2019Updated 6 years ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]☆30Feb 20, 2026Updated 4 months ago
- ☆22Jan 23, 2024Updated 2 years ago
- We aim to redefine Data Parallel libraries portabiliy, performance, programability and maintainability, by using C++ standard features, i…☆52Updated this week
- some mixture of experts architecture implementations☆27Mar 22, 2024Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Backend for the diffusion-ui frontend☆25Feb 17, 2024Updated 2 years ago
- Leo optimizer, variation of Muon that runs faster☆58Sep 6, 2025Updated 10 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Manifold-Mixup implementation for fastai V1☆19Oct 1, 2020Updated 5 years ago
- 数据库内核笔记☆14Aug 18, 2022Updated 3 years ago
- A handy plugin for copying requests/responses directly from Burp, some extra magic included.☆13Oct 15, 2021Updated 4 years ago
- ☆17Dec 11, 2022Updated 3 years ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆12Jun 10, 2024Updated 2 years ago
- ☆25Mar 15, 2023Updated 3 years ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Apr 22, 2025Updated last year
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆21Jan 24, 2025Updated last year
- -☆11Nov 21, 2020Updated 5 years 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.
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 4 months ago
- TensorRT-in-Action 是一个 GitHub 代码库，提供了使用 TensorRT 的代码示例，并有对应 Jupyter Notebook。☆15Jun 1, 2023Updated 3 years ago
- Code for AAAI 2023 accepted paper titled "Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment"☆14May 6, 2023Updated 3 years ago
- 一个很基础的Tf2.0学习教程，不需要你有tf或者keras基础，只需要有简单的python知识和一定的深度学习知识~☆10Sep 13, 2019Updated 6 years ago
- Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training☆40May 4, 2026Updated 2 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated 11 months ago
- 手搓Llama，个人学习用☆16May 21, 2024Updated 2 years ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆184Nov 11, 2025Updated 7 months ago
- Codes and data for ACL 2023 Findings paper "Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning"☆18Feb 26, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- 方便扩展的Cuda算子理解和优化框架，仅用在学习使用☆18Jun 13, 2024Updated 2 years ago
- ☆35May 25, 2026Updated last month
- ☆85Mar 3, 2026Updated 4 months ago
- Lets build a Deep Learning Framework!☆27Mar 12, 2026Updated 3 months ago
- PolEval 2021 Task 1☆15Jun 28, 2022Updated 4 years ago
- Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon☆46Mar 31, 2026Updated 3 months ago
- ☆20May 9, 2023Updated 3 years ago