thuml / depyfLinks
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
☆689Updated 2 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☆829Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆573Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆868Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,292Updated this week
- Pipeline Parallelism for PyTorch☆768Updated 10 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆362Updated 6 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆629Updated last month
- A Easy-to-understand TensorOp Matmul Tutorial☆364Updated 9 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆556Updated this week
- A library to analyze PyTorch traces.☆391Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆272Updated last year
- Cataloging released Triton kernels.☆236Updated 5 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆845Updated 5 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆377Updated last month
- Helpful tools and examples for working with flex-attention☆831Updated last week
- Applied AI experiments and examples for PyTorch☆277Updated 3 weeks ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,051Updated last year
- Shared Middle-Layer for Triton Compilation☆255Updated this week
- Ring attention implementation with flash attention☆789Updated last week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆821Updated this week
- Fast low-bit matmul kernels in Triton☆322Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆415Updated 3 weeks ago
- Fast CUDA matrix multiplication from scratch☆746Updated last year
- Puzzles for learning Triton☆1,708Updated 7 months ago
- ☆168Updated last year
- ☆219Updated this week
- Fastest kernels written from scratch☆281Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆705Updated 3 months ago
- A simple high performance CUDA GEMM implementation.☆380Updated last year
- Step-by-step optimization of CUDA SGEMM☆339Updated 3 years ago