git clone https://github.com/openppl-public/ppl.llm.serving.git Building from Source ./build.sh -DPPLNN_USE_LLM_CUDA=ON -DPPLNN_CUDA_ENABLE_NCCL=ON -DPPLNN_ENABLE_CUDA_JIT=OFF -DPPLNN_CUDA_ARCHITECTURES="'80;86;87'" -DPPLCOMMON_CUDA_ARCHITECTURES="'80;86;87'" NCCL is required if...
git clone https://github.com/openppl-public/ppl.llm.kernel.cuda.git ./build.sh -DPPLNN_CUDA_ENABLE_NCCL=ON -DPPLNN_ENABLE_CUDA_JIT=OFF -DPPLNN_CUDA_ARCHITECTURES="'80;86;87'"-DPPLCOMMON_CUDA_ARCHITECTURES="'80;86;87'" License
高洋 有两只猫,一只狗,一只玄凤的高叔叔~ 链接 链接 链接 链接 PPL.LLM已开源,欢迎star~ 发布于 2023-09-01 16:06・IP 属地北京 赞同 5 分享 收藏 写下你的评论... 登录知乎,您可以享受以下权益: 更懂你的优质内容 更专业的大咖答主 ...
LM源码git clone https://gitee.com/ascend/MindSpeed-LLM.git git clone https://github.com/NVIDIA/Megatron-LM.git # megatron从github下载,请确保网络能访问 cd Megatron-LM git checkout core_r0.8.0 cp -r megatron ../MindSpeed-LLM/ cd ../MindSpeed-LLM pip install -r requirements.txt # 安装...
HumanEval GitHub test 12.8% 12.2% MindSpeed-LLM 已支持的大模型评估数据统计如下: 模型任务MindSpeed-LLM社区模型任务MindSpeed-LLM社区 Aquila-7B BoolQ 77.3% -- Aquila2-7B BoolQ 77.8% -- Aquila2-34B BoolQ 88.0% -- Baichuan-7B BoolQ 69.0% 67.0% Baichuan-13B BoolQ 74.7% 73.6% Baichuan2-7B Bool...
// https://github.com/ColfaxResearch/cutlass-kernels/blob/a222587e6d59b93ba704853d3946fb686d8b8892/src/fmha/fmha_forward.cu#L434 using SmemLayoutVtransposed = decltype( composition(SmemLayoutKV{}, make_layout(Shape<Int<kHeadDim>, Int<kBlockN>>{}, GenRowMajor{}))); composition(SmemLayout...
Loading Oops, something went wrong. Retry 0 comments on commit 2de09b4 Please sign in to comment. Footer © 2024 GitHub, Inc. Footer navigation Terms Privacy Security Status Docs Contact Manage cookies Do not share my personal information ...
GitHub Advanced Security Enterprise-grade security features Copilot for business Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing Search or jump to... Search code, repositories, users, issues, pull requests... Provide feedback We read every piece of feedback...
* feat:add gptq for ppl * fix: add an empty line * fix: add an empty line * fix: remove an empty line * Resolve comments * Resolve comments * Resolve commentsmain (#11921) cranechu0131 committed Aug 30, 2024 Verified 1 parent 1e8c870 commit ae7302a Showing 1 changed file with ...
2Branches0Tags Code Folders and files Name Last commit message Last commit date Latest commit Cannot retrieve latest commit at this time. History 77 Commits .github/ISSUE_TEMPLATE cmake docs samples/integration-cuda src test tools .clang-format ...