编译器 / 运行时
15 条TVM、Triton、MLIR 等编译栈。
| # | 仓库 | 分类 | Stars | 最近推送 |
|---|---|---|---|---|
| 1 | jax-ml/jax Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more | 编译器 / 运行时 | 37k | 2026-11-10 10:32 UTC |
| 2 | triton-lang/triton Development repository for the Triton language and compiler | 编译器 / 运行时 | 21k | 2026-11-10 09:58 UTC |
| 3 | openai/tiktoken tiktoken is a fast BPE tokeniser for use with OpenAI's models. | 编译器 / 运行时 | 20k | 2026-11-08 08:48 UTC |
| 4 | iamgio/quarkdown 🪐 Markdown with superpowers: from ideas to papers, presentations, websites, books, and knowledge bases. | 编译器 / 运行时 | 16k | 2026-11-10 05:17 UTC |
| 5 | Konloch/bytecode-viewer A Java 8+ Jar & Android APK Reverse Engineering Suite (Decompiler, Editor, Debugger & More) | 编译器 / 运行时 | 16k | 2026-10-30 02:52 UTC |
| 6 | apache/tvm Open Machine Learning Compiler Framework | 编译器 / 运行时 | 14k | 2026-11-07 18:01 UTC |
| 7 | halide/Halide a language for fast, portable data-parallel computation | 编译器 / 运行时 | 6.6k | 2026-11-10 10:23 UTC |
| 8 | google/mtail extract internal monitoring data from application logs for collection in a timeseries database | 编译器 / 运行时 | 4.0k | 2026-03-19 00:00 UTC |
| 9 | iree-org/iree A retargetable MLIR-based machine learning compiler and runtime toolkit. | 编译器 / 运行时 | 4.0k | 2026-11-10 11:35 UTC |
| 10 | cksystemsteaching/selfie An educational software system of a tiny self-compiling C compiler, a tiny self-executing RISC-V emulator, and a tiny self-hosting RISC-V hypervisor. | 编译器 / 运行时 | 2.5k | 2026-11-07 10:52 UTC |
| 11 | Xilinx/finn Dataflow compiler for QNN inference on FPGAs | 编译器 / 运行时 | 1.1k | 2026-11-10 09:20 UTC |
| 12 | Xilinx/mlir-aie A close-to-metal Python API for programming AMD Ryzen™ AI NPUs (AI Engines), built on an open-source MLIR-based compiler toolchain. | 编译器 / 运行时 | 716 | 2026-11-10 07:50 UTC |
| 13 | kossisoroyce/timber Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference. | 编译器 / 运行时 | 690 | 2026-04-16 16:38 UTC |
| 14 | cornell-zhang/allo Allo Accelerator Design and Programming Framework (PLDI'24) | 编译器 / 运行时 | 422 | 2026-11-06 03:24 UTC |
| 15 | jkasdbt/AndroidPE AndroidPE : A programming environment from your Android smartphone allowing you to create, code and compile real Android projects based on Gradle and/or Flutter. Many other types of projects, such as Rust, Python, Type Scripts and Web. | 编译器 / 运行时 | 209 | 2026-07-21 09:18 UTC |