moritztng / grayskull-attentionLinks
Attention in SRAM on Tenstorrent Grayskull
☆36Updated 11 months ago
Alternatives and similar repositories for grayskull-attention
Users that are interested in grayskull-attention are comparing it to the libraries listed below
Sorting:
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆43Updated 3 months ago
- Tenstorrent's MLIR Based Compiler. We aim to enable developers to run AI on all configurations of Tenstorrent hardware, through an open-s…☆78Updated this week
- Tenstorrent MLIR compiler☆151Updated last week
- High-Performance SGEMM on CUDA devices☆97Updated 5 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆90Updated 2 weeks ago
- Custom PTX Instruction Benchmark☆126Updated 4 months ago
- ⭐️ TTNN Compiler for PyTorch 2 ⭐️ Enables running PyTorch models on Tenstorrent hardware using eager or compile path☆51Updated this week
- An experimental CPU backend for Triton☆135Updated last month
- Explore training for quantized models☆20Updated this week
- TritonParse is a tool designed to help developers analyze and debug Triton kernels by visualizing the compilation process and source code…☆126Updated last week
- ☆33Updated 2 weeks ago
- MLIR-based partitioning system☆103Updated this week
- A framework that support executing unmodified CUDA source code on non-NVIDIA devices.☆131Updated 6 months ago
- Buda Compiler Backend for Tenstorrent devices☆29Updated 3 months ago
- ☆110Updated 3 months ago
- ☆83Updated 8 months ago
- LLM training in simple, raw C/CUDA☆99Updated last year
- ☆20Updated 2 months ago
- IREE's PyTorch Frontend, based on Torch Dynamo.☆90Updated this week
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆62Updated 2 weeks ago
- The Riallto Open Source Project from AMD☆81Updated 3 months ago
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆100Updated last week
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆57Updated 3 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆112Updated last year
- GPUOcelot: A dynamic compilation framework for PTX☆201Updated 5 months ago
- Repository of model demos using TT-Buda☆62Updated 3 months ago
- Super fast FP32 matrix multiplication on RDNA3☆68Updated 3 months ago
- The TT-Forge FE is a graph compiler designed to optimize and transform computational graphs for deep learning models, enhancing their per…☆46Updated this week
- Collection of kernels written in Triton language☆136Updated 3 months ago
- ☆16Updated 9 months ago