master
DeepSpeed
Repository badge with D rating
View on GitHub
Grade
Name
Complexity
Churn
Issues
A
csrc\transformer\inference\csrc\transform.cu
 3 -
A
csrc\spatial\includes\spatial_cuda_layers.h
0 3 -
A
.github\workflows\nv-accelerate-v100.yml
 3 -
A
csrc\transformer\dropout_kernels.cu
 4 -
A
csrc\transformer\inference\includes\inference_cublas_wrappers.h
20 3 -
A
csrc\transformer\gelu_kernels.cu
 3 -
A
.github\workflows\nv-h100.yml
 1 -
A
csrc\transformer\inference\csrc\apply_rotary_pos_emb.cu
 4 -
A
csrc\transformer\inference\csrc\rms_norm.cu
 1 -
A
csrc\transformer\inference\csrc\gelu.cu
 3 -
A
csrc\aio\py_test\perf_sweep_utils.py
 3 1
A
csrc\transformer\inference\csrc\pointwise_ops.cu
 1 -
A
csrc\transformer\inference\csrc\softmax.cu
 4 -
A
csrc\transformer\transform_kernels.cu
 3 -
A
csrc\transformer\softmax_kernels.cu
 4 -
A
csrc\transformer\normalize_kernels.cu
 3 -
A
csrc\transformer\inference\includes\inference_cuda_layers.h
0 3 -
A
.github\workflows\nv-torch-latest-v100.yml
 3 -
A
csrc\adagrad\cpu_adagrad.cpp
26 3 -
A
csrc\aio\py_test\validate_async_io.py
 2 -