flexgen_main
FlashTrain
Repository badge with A rating
View on GitHub
Grade
Name
Complexity
Churn
Issues
A
benchmark\flexgen\bench_suite.py
 3 -
A
benchmark\third_party\DeepSpeed\csrc\includes\conversion_utils.h
94 1 -
A
benchmark\third_party\DeepSpeed\benchmarks\communication\utils.py
36 1 -
A
benchmark\third_party\DeepSpeed\benchmarks\inference\bert-bench.py
2 1 -
A
benchmark\hf_ds\bench_all_1x4.sh
 1 -
A
benchmark\third_party\DeepSpeed\csrc\includes\custom_cuda_layers.h
0 1 -
A
benchmark\third_party\DeepSpeed\benchmarks\inference\collect_results.py
13 1 -
A
benchmark\third_party\DeepSpeed\csrc\includes\dropout.h
17 1 -
A
benchmark\third_party\DeepSpeed\csrc\includes\type_shim.h
10 1 -
A
benchmark\third_party\DeepSpeed\csrc\includes\ds_transformer_cuda.h
8 1 -
A
benchmark\third_party\DeepSpeed\benchmarks\inference\requirements.txt
 1 -
A
benchmark\third_party\DeepSpeed\csrc\includes\gelu.h
5 1 -
A
benchmark\flexgen\bench_30b_1x4.sh
 1 -
A
benchmark\third_party\DeepSpeed\csrc\lamb\fused_lamb_cuda_kernel.cu
 1 -
A
benchmark\third_party\DeepSpeed\csrc\lamb\fused_lamb_cuda.cpp
6 1 -
A
benchmark\third_party\DeepSpeed\csrc\includes\quantizer.h
0 1 -
A
benchmark\flexgen\bench_dist_multi_node.sh
 1 -
A
benchmark\hf_ds\bench_ds_6.7b_1x4.sh
 1 -
A
benchmark\third_party\DeepSpeed\.github\workflows\nv-torch18-v100.yml
 1 -
A
benchmark\third_party\DeepSpeed\csrc\aio\py_lib\deepspeed_aio_thread.cpp
15 1 -