merge develop to attn-train-develop-qloop

76f2b6cd · danyao12 · 9b4c780a · 1ee99dca · 76f2b6cd · 76f2b6cd
Commit 76f2b6cd authored Jul 14, 2023 by danyao12
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/normalization.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/normalization.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/pool2d_fwd.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/pool2d_fwd.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp