sarvex/onnxruntime

main

onnxruntime

Grade	Name	Complexity	Churn	Issues
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_128_64_sm89.cubin.cc	0	1	13
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_128_40_sm86.cubin.cc	0	1	13
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_64_32_sm70.cubin.cc	0	1	12
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_128_32_sm86.cubin.cc	0	1	17
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_128_32_sm89.cubin.cc	0	1	17
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\cross_attention\fmha_mhca_fp16_128_128_sm80.cubin.cc	0	1	13
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_128_32_sm75.cubin.cc	0	1	10
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\cross_attention\fmha_mhca_fp16_128_128_sm89.cubin.cc	0	1	9
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\cross_attention\fmha_mhca_fp16_128_256_sm80.cubin.cc	0	1	9
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\flash_attention\fmha_v2_flash_attention_fp16_128_16_S_40_sm80.cubin.cc	0	1	13
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_64_32_sm86.cubin.cc	0	1	14
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_64_64_sm75.cubin.cc	0	1	10
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_64_40_sm86.cubin.cc	0	1	17
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\flash_attention\fmha_v2_flash_attention_fp16_128_16_S_40_sm86.cubin.cc	0	1	12
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\flash_attention\fmha_v2_flash_attention_fp16_128_16_S_64_sm86.cubin.cc	0	1	16
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\flash_attention\fmha_v2_flash_attention_fp16_128_16_S_64_sm80.cubin.cc	0	1	12
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\flash_attention\fmha_v2_flash_attention_fp16_128_16_S_16_sm86.cubin.cc	0	1	13
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\cross_attention\fmha_mhca_fp16_128_64_sm89.cubin.cc	0	1	14
F	onnxruntime\contrib_ops\cuda\bert\tensorrt_fused_multihead_attention\causal\fmha_v2_fp16_Causal_128_40_sm70.cubin.cc	0	1	9
F	java\src\test\java\ai\onnxruntime\OnnxMl.java	4818	1	40