| Name | Last modified | Size | Description | |
|---|---|---|---|---|
| Parent Directory | - | |||
| cumem_allocator.cpp | 2026-05-13 15:24 | 25K | ||
| custom_all_reduce.cuh | 2026-05-13 15:24 | 22K | ||
| custom_all_reduce_test.cu | 2026-05-13 15:24 | 13K | ||
| dispatch_utils.h | 2026-05-13 15:24 | 7.7K | ||
| torch_bindings.cpp | 2026-06-05 13:22 | 6.2K | ||
| type_convert.cuh | 2026-06-05 13:22 | 6.1K | ||
| spinloop.cpp | 2026-05-13 15:24 | 5.3K | ||
| custom_quickreduce.cu | 2026-05-13 15:24 | 4.8K | ||
| cache.h | 2026-05-13 15:24 | 4.4K | ||
| ops.h | 2026-06-05 13:22 | 3.9K | ||
| cumem_allocator_compat.h | 2026-05-13 15:24 | 3.7K | ||
| minimax_reduce_rms_kernel.h | 2026-06-05 13:22 | 2.2K | ||
| cuda_compat.h | 2026-05-13 15:24 | 1.9K | ||
| cuda_utils.h | 2026-05-13 15:24 | 1.4K | ||
| torch_utils.h | 2026-05-22 19:01 | 548 | ||
| cub_helpers.h | 2026-05-13 15:24 | 446 | ||
| rocm/ | 2026-05-30 04:53 | - | ||
| quickreduce/ | 2026-05-13 15:24 | - | ||
| quantization/ | 2026-06-05 13:22 | - | ||
| moe/ | 2026-06-05 13:22 | - | ||
| libtorch_stable/ | 2026-06-05 13:22 | - | ||
| cutlass_extensions/ | 2026-06-05 13:22 | - | ||
| cpu/ | 2026-06-05 13:22 | - | ||
| core/ | 2026-05-13 15:24 | - | ||
| attention/ | 2026-05-30 04:53 | - | ||