1 repositorio
Awesome GitHub RepositoriesParallel CTC Kernels
Hardware-accelerated kernels specifically optimized for parallel CTC loss computation.
Distinct from Accelerator Kernels: Focuses on the specific implementation of CTC kernels rather than general accelerator kernels for NPUs/MLUs.
Explore 1 awesome GitHub repository matching programming languages & runtimes · Parallel CTC Kernels. Refine with filters or upvote what's useful.
Awesome Parallel CTC Kernels GitHub Repositories
Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
- baidu-research/warp-ctc
baidu-research/warp-ctc
4,066Ver en GitHubwarp-ctc is a high-performance library for calculating connectionist temporal classification loss to train sequence-to-sequence deep learning models. It provides a numerical stability layer using log-space computation to prevent underflow and precision errors during probability calculations for long sequences. The library utilizes hardware-accelerated kernels to compute loss in parallel across CPU and GPU architectures. It focuses on increasing training throughput by optimizing the dynamic programming steps of the CTC algorithm. These capabilities support the training of models for speech re
Ships hardware-accelerated kernels that compute CTC loss in parallel across CPU and GPU architectures.
Cuda
