☆25Sep 23, 2026Updated last month
Alternatives and similar repositories for Awesome-MegaKernel
Users that are interested in Awesome-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:
- A repository with academic works about Kernel generation with LLM Agent☆27Oct 30, 2026Updated 2 weeks ago
- ☆11Jun 4, 2022Updated 4 years ago
- Use tensor core to calculate back-to-back HGEMM (half-precision general matrix multiplication) with MMA PTX instruction.☆13Nov 3, 2023Updated 3 years ago
- ☆27Feb 27, 2026Updated 8 months ago
- This repository contains the code for the ICLR 2026 paper “DASH: Deterministic Attention Scheduling for High-Throughput Reproducible LLM …☆15Jun 23, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Virtual Decoupled Cores: Composable Programming Framework and Runtime for Async GPUs☆27Nov 10, 2026Updated last week
- cuda best practice & notes☆10Oct 24, 2025Updated last year
- A lightweight SGLang implementation built from scratch.☆12Jul 29, 2025Updated last year
- [USENIX ATC'25] GeneralSparse: Bridging the Gap in SpMM for Pruned Large Language Model Inference on GPUs☆14Feb 4, 2026Updated 9 months ago
- ☆10Feb 6, 2025Updated last year
- Source code of the IPDPS '21 paper: "TileSpMV: A Tiled Algorithm for Sparse Matrix-Vector Multiplication on GPUs" by Yuyao Niu, Zhengyang…☆13Aug 12, 2022Updated 4 years ago
- A generic hashmap implementation in C☆13Mar 11, 2011Updated 15 years ago
- Parallel SpMV using CSR representation, built in CUDA☆14Jun 27, 2020Updated 6 years ago
- An automatic differentiation library written in C++ and CUDA☆10May 28, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Mirror of http://gitlab.hpcrl.cse.ohio-state.edu/chong/ppopp19_ae, refactoring for understanding☆17Oct 20, 2021Updated 5 years ago
- ☆13Sep 1, 2024Updated 2 years ago
- Code of Token tracking widgets☆23Jan 15, 2026Updated 10 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆79Aug 8, 2026Updated 3 months ago
- ☆19Nov 10, 2024Updated 2 years ago
- native blackwell training backward for gated linear recurrences, and a verifier that catches broken llm-generated gpu kernels☆16Nov 3, 2026Updated 2 weeks ago
- let coding agents use ncu skills analysis cuda program automatically!☆132May 25, 2026Updated 5 months ago
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆28Aug 5, 2026Updated 3 months ago
- Fast and memory-efficient exact attention☆23Updated this week
- 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.
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆145Feb 10, 2026Updated 9 months ago
- High-performance hotword biasing for WeNet C++ runtime. Fuzzy phoneme matching + multi-objective autotuning.☆13May 21, 2026Updated 5 months ago
- zLLM inference engine☆14Sep 15, 2026Updated 2 months ago
- ☆109Sep 8, 2026Updated 2 months ago
- Implementation of the ""Constant Time Updates in Hierarchical Heavy Hitters" paper, ACM SIGCOMM 2017☆21Jun 11, 2018Updated 8 years ago
- [ICML 2025] Efficiently Serving Large Multimodal Models Using EPD Disaggregation☆29Jul 11, 2026Updated 4 months ago
- A general training alignment framework for LLM training debugging. OSDI ’26 Best Paper Nominee.☆23Updated this week
- 论文semantic-human-matting的代码复现☆10Jan 13, 2021Updated 5 years ago
- Recursive Abstractive Processing for Tree-Organized Retrieval☆10May 30, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- 对qwen2.5进行微调以及知识蒸馏☆17Dec 24, 2024Updated last year
- A demo of GPT2 model trained and infered with LightSeq☆10Sep 6, 2022Updated 4 years ago
- Conditional Similarity Networks (CSNs-Tensorflow)☆10Oct 29, 2018Updated 8 years ago
- A repository for Mixed Precision Training in JAX based on Equinox.☆16Nov 2, 2025Updated last year
- ☆97Feb 5, 2026Updated 9 months ago
- An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch…☆163Sep 18, 2026Updated 2 months ago
- Optimizing Tensor Computation Graphs with Equality Saturation and Monte Carlo Tree Search☆15Aug 9, 2024Updated 2 years ago
Are these results useful?