GitHub is where people build software. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects.
FasterTransformer is built on top of CUDA, cuBLAS, cuBLASLt and C++. We provide at least one API of the following frameworks: TensorFlow, PyTorch and Triton backend. Users can integrate FasterTransformer into these frameworks directly. For supporting frameworks, we also provide example codes to de...
#Build xFasterTransformergit clone https://github.com/intel/xFasterTransformer.git xFasterTransformercdxFasterTransformer git checkout<latest-tag>#Please make sure torch is installed when run python examplemkdir build&&cdbuild cmake .. make -j ...
url = https://github.com/google-research/bert.git [submodule "OpenNMT-tf"] path = OpenNMT-tf url = https://github.com/OpenNMT/OpenNMT-tf 189 changes: 189 additions & 0 deletions 189 FasterTransformer/v3.0/CMakeLists.txt Original file line numberDiff line numberDiff line change @@ -0,...
void-maincommittedMay 2, 2023 f6cf9da bugfix void-maincommittedMay 1, 2023 40fbe48 Fix/gpt early stop (NVIDIA#584) byshiuecommittedMay 1, 2023 Verified c6e8f60 Commits on Apr 30, 2023 Merge branch 'main' of https://github.com/void-main/FasterTransformer into main void-maincommitted...
.github 3rdparty benchmark ci test_case cmake docs evaluation examples finetune include serving src tests tools .clang-format .cmake-format.py .gitignore CHANGELOG.md CMakeLists.txt CODE_OF_CONDUCT.md CODING_STANDARDS.md CONTRIBUTING.md LICENSE README.md README_CN.md SECURITY.md VERSION ci_...
forked from NVIDIA/FasterTransformer Notifications Fork 0 Star 0 Code Pull requests Actions Projects Security Insights Footer © 2024 GitHub, Inc. Footer navigation Terms Privacy Security Status Docs Contact Manage cookies Do not share my personal information ...
https://github.com/NVIDIA/FasterTransformer/tree/v3.0/ 3 INT8 量化 NVIDIA GPU 从图灵架构开始支持 INT8 Tensor Core,可以大幅提高神经网络 INT8 推理速度和吞吐量。 INT8 推理需要先将神经网络模型量化,因此官方发布了基于 TensorFlow 和 PyTorch 量化工具,用于生成 INT8量化模型以方便部署。该量化工具集成了...
下载FasterTransformer代码 可以在GitHub上下载FasterTransformer代码:https://github.com/NVIDIA/Faster...
fastertransformer for codegeex model. Contribute to CodeGeeX/codegeex-fastertransformer development by creating an account on GitHub.