thuml / depyfLinks
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
☆686Updated last month
Alternatives and similar repositories for depyf
Users that are interested in depyf are comparing it to the libraries listed below
Sorting:
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆850Updated this week
- Distributed Triton for Parallel Systems☆765Updated last week
- Pipeline Parallelism for PyTorch☆766Updated 9 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆546Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!☆334Updated 5 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,225Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆544Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆270Updated 11 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆359Updated 8 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆368Updated 2 weeks ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆827Updated 5 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆619Updated 3 weeks ago
- Ring attention implementation with flash attention☆771Updated last week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,046Updated last year
- Applied AI experiments and examples for PyTorch☆270Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆686Updated 2 months ago
- ☆210Updated this week
- Tile primitives for speedy kernels☆2,399Updated this week
- A PyTorch Native LLM Training Framework☆811Updated 5 months ago
- Helpful tools and examples for working with flex-attention☆802Updated last week
- ☆167Updated 11 months ago
- Fast low-bit matmul kernels in Triton☆303Updated this week
- Cataloging released Triton kernels.☆226Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆378Updated last month
- Microsoft Automatic Mixed Precision Library☆602Updated 8 months ago
- A library to analyze PyTorch traces.☆379Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆351Updated 3 weeks ago
- Step-by-step optimization of CUDA SGEMM☆327Updated 3 years ago
- ☆206Updated 10 months ago
- Shared Middle-Layer for Triton Compilation☆250Updated last week