Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
-
Updated
Mar 19, 2026 - Python
#
kernel-optimization
Here are 35 public repositories matching this topic...
Production-Grade Autoresearch. Ideal for GPU kernels, ML model development, feature engineering, prompt engineering, and other optimizable code.
machine-learning code-generation code-optimization prompt-engineering kernel-optimization autoresearch
-
Updated
Jul 2, 2026 - Python
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
cuda high-performance-computing triton quantization rocm gpu-kernels prompt-engineering llm-agents ai-coding kernel-optimization
-
Updated
Jun 21, 2026 - TypeScript
Custom Linux kernels purpose-built for Apple Mac hardware
performance linux-kernel arch-linux kvm qemu pvg amdgpu macpro kernel-optimization mac-hardware macos-virtualization
-
Updated
Feb 24, 2026 - Shell
Repo containing artifacts for Neurips 2025 tutorial- How to Build Agents to Generate Kernels for Faster LLMs (and Other Models!)
-
Updated
May 11, 2026 - Jupyter Notebook
Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.
gpu cuda moe gemma jetson inference-engine gpu-programming mixture-of-experts edge-ai on-device-ai blackwell llm bittensor qwen agentic-ai rtx-5090 kernel-optimization gittensor
-
Updated
Jul 5, 2026 - Cuda
AMD CDNA/RDNA (MI300 gfx942 / MI350 gfx950 / RDNA4 gfx1201) GPU kernel optimization knowledge base, packaged as a Claude Code skill. 7,400+ merged-PR references + 53 ISA-grounded synthesis pages. Inspired by MIT Han Lab's KernelWiki.
-
Updated
Jun 11, 2026 - Python
Learn Triton by building FlashAttention from scratch — V2 kernels, persistent threads, mask DSL, profiling toolkit, bilingual docs
tutorial cuda pytorch triton educational attention-mechanism gpu-programming forward-pass flash-attention kernel-optimization online-softmax
-
Updated
May 25, 2026 - Python
Extended TileLang as a unified DSL to enable high-performance kernel development for Near-Memory Computing, Distributed Memory AI Accelerators, and Networked Accelerators.
-
Updated
Jul 5, 2026 - Python
Automatic Triton kernel generation and optimization for Intel GPU, powered by Claude Code.
-
Updated
May 12, 2026 - Python
Noeris — autonomous kernel fusion discovery + Triton autotuning for LLM kernels and Gemma layer deeper fusion (A100/H100 wins).
benchmarking cuda pytorch triton autotuning gemma gpu-kernels github-actions kernel-fusion llm-training llm-inference kernel-optimization
-
Updated
May 27, 2026 - Python
METAL-SCI: a scientific compute benchmark for evolutionary LLM kernel search on Apple Silicon Metal
benchmark metal scientific-computing code-generation harness gpu-kernels apple-silicon evolutionary-search coding-agents kernel-optimization llm-harness
-
Updated
Jun 27, 2026 - Metal
A collection of high-performance CUDA kernels and experiments for learning and optimizing GPU compute primitives.
-
Updated
Jan 21, 2026 - Cuda
⚡ Low-Latency AI Windows Kernel Optimizer for Gamers & Power Users! Eliminate micro-stutters, stabilize frame-times, optimize network/ping, cut input lag, and double battery life. Unleash RAM/CPU & boost workstation rendering via low-level tweaks. 100% FREE Open-Source engine with no bloatware—unleash pro hardware tuning & responsiveness! 🚀
performance-tuning low-latency tweaking power-plan fps-booster game-booster debloat-windows windows-optimizer tweak-tool latency-reduction pc-optimization latency-optimization kernel-optimization
-
Updated
Jun 26, 2026
Optimized Ubuntu Touch for Lenovo Tab M8 HD (TB-8505F) - Kernel improvements, performance tuning, boot experience, and system optimizations for the MediaTek Helio A22 tablet
linux mediatek performance-tuning arm64 ubuntu-touch ubports kernel-optimization lenovo-tab-m8 helio-a22
-
Updated
Feb 8, 2026 - Shell
Hand-tuned NVIDIA SASS kernels for RTX 3070 Ti (GA104, sm_86): 31,910 GFLOPS HGEMM, 41,721 dense-equiv 2:4 sparse, 11,453 GFLOPS Flash Attention, no cuBLAS / cuDNN / PyTorch. Includes cuasmR, a CRAN-ready R package for cubin read/write + GPU benchmark measurement. 6-chapter tutorial + Chladni-pattern memory layout study.
sass performance-engineering cuda nvidia rstats gpu-computing r-package ampere gemm cymatics gpu-programming tensor-cores int8-quantization sparse-gemm hgemm flash-attention kernel-optimization sm-86 rtx-3070-ti cuassembler
-
Updated
Jun 5, 2026 - Cuda
Universal Windows Kernel & Hardware Optimization Suite (TR/EN)
-
Updated
Jun 15, 2026 - Batchfile
CUDA kernel optimization lab: GEMM, FlashAttention, quantization, and GPU performance learning.
cuda high-performance-computing cuda-kernels gpu-computing gemm cpp20 gpu-programming ai-inference tensor-core nanobind flashattention kernel-optimization
-
Updated
May 25, 2026 - Cuda
Learning CUDA GEMM optimization and profiling for AI infrastructure.
-
Updated
Jul 1, 2026 - Cuda
Improve this page
Add a description, image, and links to the kernel-optimization topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the kernel-optimization topic, visit your repo's landing page and select "manage topics."