当你在尝试安装autoawq-kernels包时遇到“no matching distribution found”的错误,这通常意味着pip无法在PyPI(Python Package Index)或其他配置的源中找到与你的请求匹配的包。以下是一些可能的解决步骤: 检查包名是否正确: 确保你输入的包名autoawq-kernels是正确的。有时候,包名可能因大小写
AutoAWQ Kernels is a new package that is split up from themain repositoryin order to avoid compilation times. Requirements Windows: Must use WSL2. NVIDIA: GPU: Must be compute capability 7.5 or higher. CUDA Toolkit: Must be 11.8 or higher. ...
AutoAWQ Kernels AutoAWQ Kernels is a new package that is split up from themain repositoryin order to avoid compilation times. Requirements Windows: Must use WSL2. NVIDIA: GPU: Must be compute capability 7.5 or higher. CUDA Toolkit: Must be 11.8 or higher. ...
AutoAWQ Kernels是一个专为高性能计算设计的内核包,旨在减少编译时间并支持NVIDIA和AMD GPU。通过将核心计算功能从主仓库中分离出来,该项目显著提升了开发效率,特别适用于需要快速迭代和高效计算的深度学习任务。 AutoAWQ Kernels的特点: 1. 高效计算内核包 2. 减少编译时间 3. 支持NVIDIA GPU 4. 支持AMD GPU ...
Preferautoawq-kernelsif installed. Makeautoawq-kernelsoptional and not installed by default. casper-hansenchanged the titleTriton only optional kernelsSep 10, 2024 OwnerAuthor casper-hansencommentedSep 10, 2024 The performance of the Triton kernel compared to the GEMM kernel is about the same in...
This has the following benefits: when installing AutoAWQ from source, you do not need to compile the kernels every time
Full credits go to vLLM maintainers and contributors. All I did was import the existing CUDA code. This PR imports the following work: GPTQ & AWQ Fused MOE vllm-project/vllm#2761 DeepseekMoE suppo...
AutoAWQ Kernels AutoAWQ Kernels is a new package that is split up from themain repositoryin order to avoid compilation times. Requirements Windows: Must use WSL2. NVIDIA: GPU: Must be compute capability 7.5 or higher. CUDA Toolkit: Must be 11.8 or higher. ...