syoyo / safetensors-cppLinks
Header-only safetensors loader and saver in C++
☆68Updated 4 months ago
Alternatives and similar repositories for safetensors-cpp
Users that are interested in safetensors-cpp are comparing it to the libraries listed below
Sorting:
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆16Updated 2 years ago
- An extension library of WMMA API (Tensor Core API)☆105Updated last year
- mperf是一个面向移动/嵌入式平台的算子性能调优工具箱☆188Updated 2 years ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆186Updated 7 months ago
- This is a demo how to write a high performance convolution run on apple silicon☆54Updated 3 years ago
- MatMul Performance Benchmarks for a Single CPU Core comparing both hand engineered and codegen kernels.☆134Updated 2 years ago
- llama 2 Inference☆41Updated last year
- ☆21Updated 4 years ago
- ☆150Updated 8 months ago
- Conversion to/from half-precision floating point formats☆370Updated last month
- SGEMM optimization with cuda step by step☆20Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆116Updated 4 months ago
- a simple general program language☆99Updated 3 weeks ago
- FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.☆86Updated this week
- how to design cpu gemm on x86 with avx256, that can beat openblas.☆72Updated 6 years ago
- AMD's graph optimization engine.☆249Updated this week
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆101Updated last month
- A profiler to disclose and quantify hardware features on GPUs.☆174Updated 3 years ago
- THIS REPOSITORY HAS MOVED TO github.com/nvidia/cub, WHICH IS AUTOMATICALLY MIRRORED HERE.☆84Updated last year
- A language and compiler for irregular tensor programs.☆149Updated 9 months ago
- 分层解耦的深度学习推理引擎☆75Updated 7 months ago
- Common libraries for PPL projects☆29Updated 6 months ago
- CUDA Matrix Multiplication Optimization☆222Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated last week
- An unofficial cuda assembler, for all generations of SASS, hopefully :)☆84Updated 2 years ago
- AMD ROCm Performance Primitives (RPP) library is a comprehensive high-performance computer vision library for AMD processors with HIP/Ope…☆65Updated last week
- 使用 CUDA C++ 实现的 llama 模型推理框架☆62Updated 10 months ago
- OpenAI Triton backend for Intel® GPUs☆208Updated this week
- A lightweight memory allocator for hardware-accelerated machine learning☆170Updated this week