NVIDIA / free-threaded-pythonLinks
No-GIL Python environment featuring NVIDIA Deep Learning libraries.
☆61Updated 2 months ago
Alternatives and similar repositories for free-threaded-python
Users that are interested in free-threaded-python are comparing it to the libraries listed below
Sorting:
- The CUDA target for Numba☆138Updated this week
- Numbast is a tool to build an automated pipeline that converts CUDA APIs into Numba bindings.☆47Updated last week
- ☆21Updated 3 months ago
- Collection of scripts to build PyTorch and the domain libraries from source.☆11Updated last week
- JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training☆49Updated last month
- FlexAttention w/ FlashAttention3 Support☆26Updated 8 months ago
- A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.☆112Updated this week
- A place to store reusable transformer components of my own creation or found on the interwebs☆56Updated last week
- TORCH_LOGS parser for PT2☆43Updated 3 weeks ago
- Experiment of using Tangent to autodiff triton☆79Updated last year
- ☆13Updated 4 years ago
- ☆28Updated 5 months ago
- extensible collectives library in triton☆86Updated 2 months ago
- A tracing JIT for PyTorch☆17Updated 2 years ago
- LLM training in simple, raw C/CUDA☆99Updated last year
- Make triton easier☆46Updated last year
- TritonParse is a tool designed to help developers analyze and debug Triton kernels by visualizing the compilation process and source code…☆93Updated last week
- Hacks for PyTorch☆19Updated 2 years ago
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large …☆65Updated 3 years ago
- Personal solutions to the Triton Puzzles☆19Updated 11 months ago
- ☆31Updated last week
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆43Updated 3 months ago
- PyTorch centric eager mode debugger☆47Updated 6 months ago
- ☆16Updated 9 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆77Updated last week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆90Updated 2 weeks ago
- Effective transpose on Hopper GPU☆23Updated last month
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆166Updated this week
- Automatically insert nvtx ranges to PyTorch models☆17Updated 4 years ago
- A collection of reproducible inference engine benchmarks☆31Updated 2 months ago