unixpickle / learn-ptx
Learning about CUDA by writing PTX code.
☆28Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for learn-ptx
- ☆140Updated this week
- Cataloging released Triton kernels.☆132Updated 2 months ago
- ☆133Updated 9 months ago
- Applied AI experiments and examples for PyTorch☆159Updated last week
- Simple and fast low-bit matmul kernels in CUDA / Triton☆133Updated this week
- extensible collectives library in triton☆61Updated last month
- Small scale distributed training of sequential deep learning models, built on Numpy and MPI.☆95Updated last year
- This repository contains the experimental PyTorch native float8 training UX☆211Updated 3 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆183Updated last month
- ☆162Updated 3 months ago
- Collection of kernels written in Triton language☆63Updated last week
- ring-attention experiments☆95Updated 3 weeks ago
- ☆82Updated 8 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆87Updated 3 months ago
- CUDA Matrix Multiplication Optimization☆139Updated 3 months ago
- Experiment of using Tangent to autodiff triton☆71Updated 9 months ago
- ☆32Updated 5 months ago
- ☆43Updated this week
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆35Updated 3 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆46Updated this week
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆66Updated 5 months ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆34Updated 5 months ago
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…☆146Updated this week
- LLM training in simple, raw C/CUDA☆86Updated 6 months ago
- ☆156Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆107Updated 5 months ago
- ☆88Updated 2 months ago
- ☆72Updated 4 months ago
- A minimal implementation of vllm.☆30Updated 3 months ago
- An implementation of the transformer architecture onto an Nvidia CUDA kernel☆157Updated last year