This is the Windows app named DeepGEMM whose latest release can be downloaded as Stablereleasev2.1.0sourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named DeepGEMM with OnWorks for free.
Siga estas instruções para executar este aplicativo:
- 1. Baixe este aplicativo em seu PC.
- 2. Entre em nosso gerenciador de arquivos https://www.onworks.net/myfiles.php?username=XXXXX com o nome de usuário que você deseja.
- 3. Carregue este aplicativo em tal gerenciador de arquivos.
- 4. Inicie qualquer emulador on-line OS OnWorks a partir deste site, mas um emulador on-line melhor do Windows.
- 5. No sistema operacional OnWorks Windows que você acabou de iniciar, acesse nosso gerenciador de arquivos https://www.onworks.net/myfiles.php?username=XXXXX com o nome de usuário que deseja.
- 6. Baixe o aplicativo e instale-o.
- 7. Baixe o Wine de seus repositórios de software de distribuição Linux. Depois de instalado, você pode clicar duas vezes no aplicativo para executá-lo com o Wine. Você também pode experimentar o PlayOnLinux, uma interface sofisticada do Wine que o ajudará a instalar programas e jogos populares do Windows.
Wine é uma forma de executar software Windows no Linux, mas sem a necessidade de Windows. Wine é uma camada de compatibilidade do Windows de código aberto que pode executar programas do Windows diretamente em qualquer desktop Linux. Essencialmente, o Wine está tentando reimplementar o suficiente do Windows do zero para que possa executar todos os aplicativos do Windows sem realmente precisar do Windows.
SCREENSHOTS
Ad
GEMM profundo
DESCRIÇÃO
DeepGEMM is a specialized CUDA library for efficient, high-performance general matrix multiplication (GEMM) operations, with particular focus on low-precision formats such as FP8 (and experimental support for BF16). The library is designed to work cleanly and simply, avoiding overly templated or heavily abstracted code, while still delivering performance that rivals expert-tuned libraries. It supports both standard and “grouped” GEMMs, which is useful for architectures like Mixture of Experts (MoE) that require segmented matrix multiplications. One distinguishing aspect is that DeepGEMM compiles its kernels at runtime (via a lightweight Just-In-Time (JIT) module), so users don’t need to precompile CUDA kernels before installation. Despite its lean design, it includes scaling strategies (fine-grained scaling) and optimizations inspired by cutting edge systems (drawing from ideas in CUTLASS, CuTe) but in a more streamlined form.
Recursos
- High-performance GEMM kernels focused on FP8 precision, with optional BF16 support
- Support for grouped GEMM (segmented matrix operations) useful for MoE scenarios
- Runtime JIT compilation of kernels (no heavy ahead-of-time kernel compilation needed)
- Clean, modular code structure (less dependence on heavy template programming)
- Fine-grained scaling strategies (to adapt precision dynamically)
- Benchmark and test suite (e.g. test_fp8.py), performance monitoring, and ongoing issue tracking
Linguagem de Programação
C + +
Categorias
This is an application that can also be fetched from https://sourceforge.net/projects/deepgemm.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
