A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
Rules for building and handling Docker images with Bazel
bazel build rules to use boost in bazel projects
最近一年贡献：0 次
最长连续贡献：0 日
最近连续贡献：0 日
贡献度的统计数据包括代码提交、创建任务 / Pull Request、合并 Pull Request，其中代码提交的次数需本地配置的 git 邮箱是 Gitee 帐号已确认绑定的才会被统计。