thuml / depyfLinks
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
☆706Updated 3 months ago
Alternatives and similar repositories for depyf
Users that are interested in depyf are comparing it to the libraries listed below
Sorting:
- Distributed Compiler based on Triton for Parallel Systems☆930Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆635Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆273Updated last year
- Puzzles for learning Triton, play it with minimal environment configuration!☆442Updated 7 months ago
- Pipeline Parallelism for PyTorch☆775Updated 11 months ago
- A Quirky Assortment of CuTe Kernels☆374Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆391Updated 2 months ago
- A library to analyze PyTorch traces.☆398Updated last week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆563Updated 2 weeks ago
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆842Updated last week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,472Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆653Updated 3 weeks ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆193Updated this week
- Applied AI experiments and examples for PyTorch☆289Updated 2 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆368Updated 10 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆1,629Updated this week
- Cataloging released Triton kernels.☆246Updated 6 months ago
- Zero Bubble Pipeline Parallelism☆411Updated 2 months ago
- Ring attention implementation with flash attention☆828Updated last week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆887Updated 7 months ago
- ☆227Updated this week
- kernels, of the mega variety☆461Updated 2 months ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆200Updated this week
- ☆227Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆730Updated 4 months ago
- Fastest kernels written from scratch☆308Updated 3 months ago
- Step-by-step optimization of CUDA SGEMM☆362Updated 3 years ago
- Microsoft Automatic Mixed Precision Library☆616Updated 10 months ago
- Fast low-bit matmul kernels in Triton☆338Updated this week
- Shared Middle-Layer for Triton Compilation☆260Updated this week