| .. |
| cublas_common.h | refactor part 2, moving stuff into common files so that we can later nicely separate out all the kernels as well | 2 years ago |
| cuda_common.h | moved device utilities into a separate file, and follow-up cleanup | 2 years ago |
| cuda_utils.cuh | moved device utilities into a separate file, and follow-up cleanup | 2 years ago |
| cudnn_att.cpp | moved device utilities into a separate file, and follow-up cleanup | 2 years ago |
| cudnn_att.h | moved device utilities into a separate file, and follow-up cleanup | 2 years ago |
| dataloader.h | Remove file size - not used | 2 years ago |
| encoder.cuh | also move the launchers | 2 years ago |
| logger.h | more refactor | 2 years ago |
| mfu.h | add new file llmc/mfu.h for MFU calculations for different GPUs | 2 years ago |
| rand.h | Add clarification on Box-Muller | 2 years ago |
| sampler.h | refactor part 2, moving stuff into common files so that we can later nicely separate out all the kernels as well | 2 years ago |
| tokenizer.h | experiment with adding the llmc lib directory | 2 years ago |
| utils.h | more refactor | 2 years ago |