{"schemaVersion":1,"deviceProperties":[{"id":0,"name":"NVIDIA GeForce RTX 5080","totalGlobalMem":16608133120,"computeMajor":12,"computeMinor":0,"maxThreadsPerBlock":1024,"maxThreadsPerMultiprocessor":1536,"regsPerBlock":65536,"warpSize":32,"sharedMemPerBlock":49152,"numSms":84,"regsPerMultiprocessor":65536,"sharedMemPerBlockOptin":101376,"sharedMemPerMultiprocessor":102400}],"trace_id":"BF4B19F1E37244F7A3F59133C3550588","profile_memory":1,"cuda_driver_version":13020,"record_shapes":1,"cuda_runtime_version":13020,"cupti_version":130201,"host_name":"42a7252ec2fb","displayTimeUnit":"ms","baseTimeNanoseconds":1782967788000000000,"traceEvents":[{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":912,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":912,"tid":0,"args":{"labels":"CPU"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":912,"tid":0,"args":{"sort_index":912}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":0,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":0,"tid":0,"args":{"labels":"GPU 0"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":0,"tid":0,"args":{"sort_index":5000000}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":1,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":1,"tid":0,"args":{"labels":"GPU 1"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":1,"tid":0,"args":{"sort_index":5000001}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":2,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":2,"tid":0,"args":{"labels":"GPU 2"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":2,"tid":0,"args":{"sort_index":5000002}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":3,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":3,"tid":0,"args":{"labels":"GPU 3"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":3,"tid":0,"args":{"sort_index":5000003}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":4,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":4,"tid":0,"args":{"labels":"GPU 4"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":4,"tid":0,"args":{"sort_index":5000004}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":5,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":5,"tid":0,"args":{"labels":"GPU 5"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":5,"tid":0,"args":{"sort_index":5000005}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":6,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":6,"tid":0,"args":{"labels":"GPU 6"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":6,"tid":0,"args":{"sort_index":5000006}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":7,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":7,"tid":0,"args":{"labels":"GPU 7"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":7,"tid":0,"args":{"sort_index":5000007}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":8,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":8,"tid":0,"args":{"labels":"GPU 8"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":8,"tid":0,"args":{"sort_index":5000008}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":9,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":9,"tid":0,"args":{"labels":"GPU 9"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":9,"tid":0,"args":{"sort_index":5000009}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":10,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":10,"tid":0,"args":{"labels":"GPU 10"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":10,"tid":0,"args":{"sort_index":5000010}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":11,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":11,"tid":0,"args":{"labels":"GPU 11"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":11,"tid":0,"args":{"sort_index":5000011}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":12,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":12,"tid":0,"args":{"labels":"GPU 12"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":12,"tid":0,"args":{"sort_index":5000012}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":13,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":13,"tid":0,"args":{"labels":"GPU 13"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":13,"tid":0,"args":{"sort_index":5000013}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":14,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":14,"tid":0,"args":{"labels":"GPU 14"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":14,"tid":0,"args":{"sort_index":5000014}},{"ph":"M","name":"process_name","ts":3147904769257.925,"pid":15,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3147904769257.925,"pid":15,"tid":0,"args":{"labels":"GPU 15"}},{"ph":"M","name":"process_sort_index","ts":3147904769257.925,"pid":15,"tid":0,"args":{"sort_index":5000015}},{"ph":"M","name":"thread_name","ts":3147904769257.925,"pid":0,"tid":7,"args":{"name":"stream 7 "}},{"ph":"M","name":"thread_sort_index","ts":3147904769257.925,"pid":0,"tid":7,"args":{"sort_index":7}},{"ph":"M","name":"thread_name","ts":3147904769257.925,"pid":912,"tid":912,"args":{"name":"thread 912 (python)"}},{"ph":"M","name":"thread_sort_index","ts":3147904769257.925,"pid":912,"tid":912,"args":{"sort_index":912}},{"ph":"M","name":"thread_name","ts":3147904769257.925,"pid":912,"tid":912,"args":{"name":"thread 912 (python)"}},{"ph":"M","name":"thread_sort_index","ts":3147904769257.925,"pid":912,"tid":912,"args":{"sort_index":912}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#3","pid":912,"tid":912,"ts":3147904769353.56,"dur":473.95,"args":{"External id":1,"Record function id":0,"Ev Idx":0}},{"ph":"X","cat":"cpu_op","name":"TorchDynamo Cache Lookup","pid":912,"tid":912,"ts":3147904769380.29,"dur":9.026,"args":{"External id":2,"Record function id":0,"Ev Idx":1}},{"ph":"X","cat":"cpu_op","name":"Torch-Compiled Region: 0/0","pid":912,"tid":912,"ts":3147904769391.562,"dur":415.293,"args":{"External id":3,"Record function id":0,"Ev Idx":2}},{"ph":"X","cat":"cpu_op","name":"Pregraph bytecode","pid":912,"tid":912,"ts":3147904769401.309,"dur":28.482,"args":{"External id":4,"Record function id":0,"Ev Idx":3}},{"ph":"X","cat":"cpu_op","name":"AOTDispatcher Runtime Wrapper Prologue","pid":912,"tid":912,"ts":3147904769445.779,"dur":8.614,"args":{"External id":5,"Record function id":0,"Ev Idx":4}},{"ph":"X","cat":"cpu_op","name":"CompiledFunction","pid":912,"tid":912,"ts":3147904769523.058,"dur":275.753,"args":{"External id":6,"Sequence number":24,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1],[1024,1]],"Input Dims":[[2048,1024],[2048],[128,1024]],"Ev Idx":5}},{"ph":"X","cat":"user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":912,"tid":912,"ts":3147904769540.374,"dur":234.345,"args":{"External id":7,"Record function id":0,"scope":"user_scope","Ev Idx":6}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":912,"tid":912,"ts":3147904769611.709,"dur":32.517,"args":{"External id":8,"Record function id":0,"Concrete Inputs":["","","","1","1",""],"Input type":["float","float","float","Scalar","Scalar","float"],"Input Strides":[[1],[1024,1],[1,1024],[],[],[2048,1]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[],[128,2048]],"Ev Idx":7}},{"ph":"X","cat":"cpu_op","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":912,"tid":912,"ts":3147904769709.355,"dur":23.79,"args":{"External id":9,"Record function id":0,"Ev Idx":8,"Input Dims":[[128,2048],[128,1],[128,1],[128],[128,2048],[],[]],"Input Strides":[[2048,1],[1,1],[1,1],[1],[2048,1],[],[]],"Input type":["float","float","float","float","float","Scalar","Scalar"],"Concrete Inputs":["","","","","","128","2048"],"stream":0,"num_warps":8,"kernel_backend":"triton","kernel_name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","num_stages":1,"kernel_file":"/tmp/torchinductor_root/jt/cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe.py","kernel_hash":"cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe","kernel_kwargs":"XBLOCK=2,R0_BLOCK=1024"}},{"ph":"X","cat":"cpu_op","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":912,"tid":912,"ts":3147904769753.467,"dur":14.534,"args":{"External id":10,"Record function id":0,"Ev Idx":9,"Input Dims":[[128],[],[]],"Input Strides":[[1],[],[]],"Input type":["float","Scalar","Scalar"],"Concrete Inputs":["","1","128"],"stream":0,"num_warps":2,"kernel_backend":"triton","kernel_name":"triton_per_fused__assert_async_abs_all_le_sub_1","num_stages":1,"kernel_file":"/tmp/torchinductor_root/n7/cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65.py","kernel_hash":"cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65","kernel_kwargs":"XBLOCK=1"}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#4","pid":912,"tid":912,"ts":3147904769845.25,"dur":284.458,"args":{"External id":11,"Record function id":0,"Ev Idx":10}},{"ph":"X","cat":"cpu_op","name":"TorchDynamo Cache Lookup","pid":912,"tid":912,"ts":3147904769867.587,"dur":8.923,"args":{"External id":12,"Record function id":0,"Ev Idx":11}},{"ph":"X","cat":"cpu_op","name":"Torch-Compiled Region: 0/0","pid":912,"tid":912,"ts":3147904769877.812,"dur":231.828,"args":{"External id":13,"Record function id":0,"Ev Idx":12}},{"ph":"X","cat":"cpu_op","name":"Pregraph bytecode","pid":912,"tid":912,"ts":3147904769883.887,"dur":3.218,"args":{"External id":14,"Record function id":0,"Ev Idx":13}},{"ph":"X","cat":"cpu_op","name":"AOTDispatcher Runtime Wrapper Prologue","pid":912,"tid":912,"ts":3147904769899.48,"dur":8.878,"args":{"External id":15,"Record function id":0,"Ev Idx":14}},{"ph":"X","cat":"cpu_op","name":"CompiledFunction","pid":912,"tid":912,"ts":3147904769918.145,"dur":183.557,"args":{"External id":16,"Sequence number":25,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1],[1024,1]],"Input Dims":[[2048,1024],[2048],[128,1024]],"Ev Idx":15}},{"ph":"X","cat":"user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":912,"tid":912,"ts":3147904769928.588,"dur":149.759,"args":{"External id":17,"Record function id":0,"scope":"user_scope","Ev Idx":16}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":912,"tid":912,"ts":3147904769949.448,"dur":30.865,"args":{"External id":18,"Record function id":0,"Concrete Inputs":["","","","1","1",""],"Input type":["float","float","float","Scalar","Scalar","float"],"Input Strides":[[1],[1024,1],[1,1024],[],[],[2048,1]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[],[128,2048]],"Ev Idx":17}},{"ph":"X","cat":"cpu_op","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":912,"tid":912,"ts":3147904770017.957,"dur":22.676,"args":{"External id":19,"Record function id":0,"Ev Idx":18,"Input Dims":[[128,2048],[128,1],[128,1],[128],[128,2048],[],[]],"Input Strides":[[2048,1],[1,1],[1,1],[1],[2048,1],[],[]],"Input type":["float","float","float","float","float","Scalar","Scalar"],"Concrete Inputs":["","","","","","128","2048"],"stream":0,"num_warps":8,"kernel_backend":"triton","kernel_name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","num_stages":1,"kernel_file":"/tmp/torchinductor_root/jt/cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe.py","kernel_hash":"cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe","kernel_kwargs":"XBLOCK=2,R0_BLOCK=1024"}},{"ph":"X","cat":"cpu_op","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":912,"tid":912,"ts":3147904770057.566,"dur":14.043,"args":{"External id":20,"Record function id":0,"Ev Idx":19,"Input Dims":[[128],[],[]],"Input Strides":[[1],[],[]],"Input type":["float","Scalar","Scalar"],"Concrete Inputs":["","1","128"],"stream":0,"num_warps":2,"kernel_backend":"triton","kernel_name":"triton_per_fused__assert_async_abs_all_le_sub_1","num_stages":1,"kernel_file":"/tmp/torchinductor_root/n7/cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65.py","kernel_hash":"cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65","kernel_kwargs":"XBLOCK=1"}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#5","pid":912,"tid":912,"ts":3147904770146.377,"dur":273.781,"args":{"External id":21,"Record function id":0,"Ev Idx":20}},{"ph":"X","cat":"cpu_op","name":"TorchDynamo Cache Lookup","pid":912,"tid":912,"ts":3147904770168.586,"dur":8.568,"args":{"External id":22,"Record function id":0,"Ev Idx":21}},{"ph":"X","cat":"cpu_op","name":"Torch-Compiled Region: 0/0","pid":912,"tid":912,"ts":3147904770178.442,"dur":221.959,"args":{"External id":23,"Record function id":0,"Ev Idx":22}},{"ph":"X","cat":"cpu_op","name":"Pregraph bytecode","pid":912,"tid":912,"ts":3147904770183.95,"dur":2.958,"args":{"External id":24,"Record function id":0,"Ev Idx":23}},{"ph":"X","cat":"cpu_op","name":"AOTDispatcher Runtime Wrapper Prologue","pid":912,"tid":912,"ts":3147904770196.845,"dur":8.203,"args":{"External id":25,"Record function id":0,"Ev Idx":24}},{"ph":"X","cat":"cpu_op","name":"CompiledFunction","pid":912,"tid":912,"ts":3147904770214.507,"dur":178.109,"args":{"External id":26,"Sequence number":26,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1],[1024,1]],"Input Dims":[[2048,1024],[2048],[128,1024]],"Ev Idx":25}},{"ph":"X","cat":"user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":912,"tid":912,"ts":3147904770224.568,"dur":146.484,"args":{"External id":27,"Record function id":0,"scope":"user_scope","Ev Idx":26}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":912,"tid":912,"ts":3147904770244.773,"dur":30.577,"args":{"External id":28,"Record function id":0,"Concrete Inputs":["","","","1","1",""],"Input type":["float","float","float","Scalar","Scalar","float"],"Input Strides":[[1],[1024,1],[1,1024],[],[],[2048,1]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[],[128,2048]],"Ev Idx":27}},{"ph":"X","cat":"cpu_op","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":912,"tid":912,"ts":3147904770312.115,"dur":21.711,"args":{"External id":29,"Record function id":0,"Ev Idx":28,"Input Dims":[[128,2048],[128,1],[128,1],[128],[128,2048],[],[]],"Input Strides":[[2048,1],[1,1],[1,1],[1],[2048,1],[],[]],"Input type":["float","float","float","float","float","Scalar","Scalar"],"Concrete Inputs":["","","","","","128","2048"],"stream":0,"num_warps":8,"kernel_backend":"triton","kernel_name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","num_stages":1,"kernel_file":"/tmp/torchinductor_root/jt/cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe.py","kernel_hash":"cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe","kernel_kwargs":"XBLOCK=2,R0_BLOCK=1024"}},{"ph":"X","cat":"cpu_op","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":912,"tid":912,"ts":3147904770350.418,"dur":14.164,"args":{"External id":30,"Record function id":0,"Ev Idx":29,"Input Dims":[[128],[],[]],"Input Strides":[[1],[],[]],"Input type":["float","Scalar","Scalar"],"Concrete Inputs":["","1","128"],"stream":0,"num_warps":2,"kernel_backend":"triton","kernel_name":"triton_per_fused__assert_async_abs_all_le_sub_1","num_stages":1,"kernel_file":"/tmp/torchinductor_root/n7/cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65.py","kernel_hash":"cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65","kernel_kwargs":"XBLOCK=1"}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#6","pid":912,"tid":912,"ts":3147904770436.897,"dur":306.758,"args":{"External id":31,"Record function id":0,"Ev Idx":30}},{"ph":"X","cat":"cpu_op","name":"TorchDynamo Cache Lookup","pid":912,"tid":912,"ts":3147904770458.355,"dur":8.502,"args":{"External id":32,"Record function id":0,"Ev Idx":31}},{"ph":"X","cat":"cpu_op","name":"Torch-Compiled Region: 0/0","pid":912,"tid":912,"ts":3147904770468.091,"dur":229.8,"args":{"External id":33,"Record function id":0,"Ev Idx":32}},{"ph":"X","cat":"cpu_op","name":"Pregraph bytecode","pid":912,"tid":912,"ts":3147904770473.784,"dur":3.015,"args":{"External id":34,"Record function id":0,"Ev Idx":33}},{"ph":"X","cat":"cpu_op","name":"AOTDispatcher Runtime Wrapper Prologue","pid":912,"tid":912,"ts":3147904770486.414,"dur":7.952,"args":{"External id":35,"Record function id":0,"Ev Idx":34}},{"ph":"X","cat":"cpu_op","name":"CompiledFunction","pid":912,"tid":912,"ts":3147904770503.664,"dur":181.947,"args":{"External id":36,"Sequence number":27,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1],[1024,1]],"Input Dims":[[2048,1024],[2048],[128,1024]],"Ev Idx":35}},{"ph":"X","cat":"user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":912,"tid":912,"ts":3147904770513.779,"dur":144.783,"args":{"External id":37,"Record function id":0,"scope":"user_scope","Ev Idx":36}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":912,"tid":912,"ts":3147904770537.431,"dur":30.366,"args":{"External id":38,"Record function id":0,"Concrete Inputs":["","","","1","1",""],"Input type":["float","float","float","Scalar","Scalar","float"],"Input Strides":[[1],[1024,1],[1,1024],[],[],[2048,1]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[],[128,2048]],"Ev Idx":37}},{"ph":"X","cat":"cpu_op","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":912,"tid":912,"ts":3147904770601.415,"dur":21.533,"args":{"External id":39,"Record function id":0,"Ev Idx":38,"Input Dims":[[128,2048],[128,1],[128,1],[128],[128,2048],[],[]],"Input Strides":[[2048,1],[1,1],[1,1],[1],[2048,1],[],[]],"Input type":["float","float","float","float","float","Scalar","Scalar"],"Concrete Inputs":["","","","","","128","2048"],"stream":0,"num_warps":8,"kernel_backend":"triton","kernel_name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","num_stages":1,"kernel_file":"/tmp/torchinductor_root/jt/cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe.py","kernel_hash":"cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe","kernel_kwargs":"XBLOCK=2,R0_BLOCK=1024"}},{"ph":"X","cat":"cpu_op","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":912,"tid":912,"ts":3147904770638.707,"dur":13.465,"args":{"External id":40,"Record function id":0,"Ev Idx":39,"Input Dims":[[128],[],[]],"Input Strides":[[1],[],[]],"Input type":["float","Scalar","Scalar"],"Concrete Inputs":["","1","128"],"stream":0,"num_warps":2,"kernel_backend":"triton","kernel_name":"triton_per_fused__assert_async_abs_all_le_sub_1","num_stages":1,"kernel_file":"/tmp/torchinductor_root/n7/cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65.py","kernel_hash":"cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65","kernel_kwargs":"XBLOCK=1"}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#7","pid":912,"tid":912,"ts":3147904770775.882,"dur":271.67,"args":{"External id":41,"Record function id":0,"Ev Idx":40}},{"ph":"X","cat":"cpu_op","name":"TorchDynamo Cache Lookup","pid":912,"tid":912,"ts":3147904770797.784,"dur":8.709,"args":{"External id":42,"Record function id":0,"Ev Idx":41}},{"ph":"X","cat":"cpu_op","name":"Torch-Compiled Region: 0/0","pid":912,"tid":912,"ts":3147904770807.761,"dur":220.121,"args":{"External id":43,"Record function id":0,"Ev Idx":42}},{"ph":"X","cat":"cpu_op","name":"Pregraph bytecode","pid":912,"tid":912,"ts":3147904770813.584,"dur":2.945,"args":{"External id":44,"Record function id":0,"Ev Idx":43}},{"ph":"X","cat":"cpu_op","name":"AOTDispatcher Runtime Wrapper Prologue","pid":912,"tid":912,"ts":3147904770825.979,"dur":8.091,"args":{"External id":45,"Record function id":0,"Ev Idx":44}},{"ph":"X","cat":"cpu_op","name":"CompiledFunction","pid":912,"tid":912,"ts":3147904770843.486,"dur":176.942,"args":{"External id":46,"Sequence number":28,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1],[1024,1]],"Input Dims":[[2048,1024],[2048],[128,1024]],"Ev Idx":45}},{"ph":"X","cat":"user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":912,"tid":912,"ts":3147904770853.437,"dur":144.943,"args":{"External id":47,"Record function id":0,"scope":"user_scope","Ev Idx":46}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":912,"tid":912,"ts":3147904770873.58,"dur":30.44,"args":{"External id":48,"Record function id":0,"Concrete Inputs":["","","","1","1",""],"Input type":["float","float","float","Scalar","Scalar","float"],"Input Strides":[[1],[1024,1],[1,1024],[],[],[2048,1]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[],[128,2048]],"Ev Idx":47}},{"ph":"X","cat":"cpu_op","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":912,"tid":912,"ts":3147904770937.282,"dur":21.062,"args":{"External id":49,"Record function id":0,"Ev Idx":48,"Input Dims":[[128,2048],[128,1],[128,1],[128],[128,2048],[],[]],"Input Strides":[[2048,1],[1,1],[1,1],[1],[2048,1],[],[]],"Input type":["float","float","float","float","float","Scalar","Scalar"],"Concrete Inputs":["","","","","","128","2048"],"stream":0,"num_warps":8,"kernel_backend":"triton","kernel_name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","num_stages":1,"kernel_file":"/tmp/torchinductor_root/jt/cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe.py","kernel_hash":"cjtljxnp5kzdo7h3ehru3inh6njwu4nvcy5iwh5cgqqcbkvh35oe","kernel_kwargs":"XBLOCK=2,R0_BLOCK=1024"}},{"ph":"X","cat":"cpu_op","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":912,"tid":912,"ts":3147904770977.25,"dur":14.716,"args":{"External id":50,"Record function id":0,"Ev Idx":49,"Input Dims":[[128],[],[]],"Input Strides":[[1],[],[]],"Input type":["float","Scalar","Scalar"],"Concrete Inputs":["","1","128"],"stream":0,"num_warps":2,"kernel_backend":"triton","kernel_name":"triton_per_fused__assert_async_abs_all_le_sub_1","num_stages":1,"kernel_file":"/tmp/torchinductor_root/n7/cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65.py","kernel_hash":"cn7zhldscbuk7kmpqzrpokhxyrrwfyq45kia262lsxsr7qsc6g65","kernel_kwargs":"XBLOCK=1"}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769568.181,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269316173824,"finished":false,"Ev Idx":50}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769651.047,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441489920,"finished":false,"Ev Idx":51}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769654.1,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441490432,"finished":false,"Ev Idx":52}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769656.773,"args":{"Total Reserved":60817408,"Total Allocated":45623808,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441490944,"finished":false,"Ev Idx":53}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769673.514,"args":{"Total Reserved":60817408,"Total Allocated":46672384,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269445148672,"finished":false,"Ev Idx":54}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769771.365,"args":{"Total Reserved":60817408,"Total Allocated":46671872,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441490944,"finished":false,"Ev Idx":55}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769815.182,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269317222400,"finished":false,"Ev Idx":56}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769815.89,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441488896,"finished":false,"Ev Idx":57}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769816.277,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441489408,"finished":false,"Ev Idx":58}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769818.239,"args":{"Total Reserved":60817408,"Total Allocated":44573696,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269444100096,"finished":false,"Ev Idx":59}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769940.388,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269317222400,"finished":false,"Ev Idx":60}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769986.745,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441490944,"finished":false,"Ev Idx":61}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769989.693,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441491456,"finished":false,"Ev Idx":62}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769991.654,"args":{"Total Reserved":60817408,"Total Allocated":45623808,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441491968,"finished":false,"Ev Idx":63}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904769993.653,"args":{"Total Reserved":60817408,"Total Allocated":46672384,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269444100096,"finished":false,"Ev Idx":64}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770074.978,"args":{"Total Reserved":60817408,"Total Allocated":46671872,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441491968,"finished":false,"Ev Idx":65}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770117.553,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269316173824,"finished":false,"Ev Idx":66}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770118.265,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441489920,"finished":false,"Ev Idx":67}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770118.708,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441490432,"finished":false,"Ev Idx":68}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770120.438,"args":{"Total Reserved":60817408,"Total Allocated":44573696,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269445148672,"finished":false,"Ev Idx":69}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770235.812,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269316173824,"finished":false,"Ev Idx":70}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770281.498,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441491968,"finished":false,"Ev Idx":71}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770284.44,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441492480,"finished":false,"Ev Idx":72}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770286.395,"args":{"Total Reserved":60817408,"Total Allocated":45623808,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441492992,"finished":false,"Ev Idx":73}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770291.287,"args":{"Total Reserved":60817408,"Total Allocated":46672384,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269445148672,"finished":false,"Ev Idx":74}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770367.816,"args":{"Total Reserved":60817408,"Total Allocated":46671872,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441492992,"finished":false,"Ev Idx":75}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770408.097,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269317222400,"finished":false,"Ev Idx":76}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770408.767,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441490944,"finished":false,"Ev Idx":77}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770409.152,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441491456,"finished":false,"Ev Idx":78}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770410.945,"args":{"Total Reserved":60817408,"Total Allocated":44573696,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269444100096,"finished":false,"Ev Idx":79}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770524.922,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269317222400,"finished":false,"Ev Idx":80}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770574.199,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441492992,"finished":false,"Ev Idx":81}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770577.421,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441493504,"finished":false,"Ev Idx":82}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770579.384,"args":{"Total Reserved":60817408,"Total Allocated":45623808,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441494016,"finished":false,"Ev Idx":83}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770581.121,"args":{"Total Reserved":60817408,"Total Allocated":46672384,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269444100096,"finished":false,"Ev Idx":84}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770655.287,"args":{"Total Reserved":60817408,"Total Allocated":46671872,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441494016,"finished":false,"Ev Idx":85}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770731.055,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269316173824,"finished":false,"Ev Idx":86}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770732.054,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441491968,"finished":false,"Ev Idx":87}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770732.434,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441492480,"finished":false,"Ev Idx":88}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770734.302,"args":{"Total Reserved":60817408,"Total Allocated":44573696,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269445148672,"finished":false,"Ev Idx":89}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770864.551,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269316173824,"finished":false,"Ev Idx":90}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770910.323,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441494016,"finished":false,"Ev Idx":91}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770913.269,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441494528,"finished":false,"Ev Idx":92}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770915.109,"args":{"Total Reserved":60817408,"Total Allocated":45623808,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":133269441495040,"finished":false,"Ev Idx":93}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770916.808,"args":{"Total Reserved":60817408,"Total Allocated":46672384,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":133269445148672,"finished":false,"Ev Idx":94}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904770995.222,"args":{"Total Reserved":60817408,"Total Allocated":46671872,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441495040,"finished":false,"Ev Idx":95}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904771035.697,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269317222400,"finished":false,"Ev Idx":96}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904771036.374,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441492992,"finished":false,"Ev Idx":97}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904771036.682,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":133269441493504,"finished":false,"Ev Idx":98}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":912,"tid":912,"ts":3147904771038.435,"args":{"Total Reserved":60817408,"Total Allocated":44573696,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":133269444100096,"finished":false,"Ev Idx":99}},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":912,"tid":912,"ts":3147904769629.112,"dur":0.625,"args":{"External id":8,"cbid":200,"correlation":2279}},{"ph":"f","id":2279,"pid":912,"tid":912,"ts":3147904769629.112,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":912,"tid":912,"ts":3147904769631.696,"dur":0.315,"args":{"External id":8,"cbid":51,"correlation":2282}},{"ph":"s","id":2282,"pid":912,"tid":912,"ts":3147904769631.696,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3147904769641.967,"dur":13.984,"args":{"External id":8,"queued":0,"device":0,"context":1,"stream":7,"correlation":2283,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2283,"pid":0,"tid":7,"ts":3147904769641.967,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904769632.261,"dur":8.935,"args":{"External id":8,"cbid":307,"correlation":2283}},{"ph":"s","id":2283,"pid":912,"tid":912,"ts":3147904769632.261,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":0,"tid":7,"ts":3147904769732.816,"dur":2.656,"args":{"External id":9,"queued":0,"device":0,"context":1,"stream":7,"correlation":2308,"registers per thread":40,"shared memory":64,"blocks per SM":0.761905,"warps per SM":6.095238,"grid":[64,1,1],"block":[256,1,1],"est. achieved occupancy %":13,"occupancy":{"activeBlocksPerMultiprocessor":6,"limitingFactors":"WARPS|REGS","blockLimitRegs":6,"blockLimitSharedMem":88,"blockLimitWarps":6,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":10240,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2308,"pid":0,"tid":7,"ts":3147904769732.816,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904769723.525,"dur":8.29,"args":{"External id":9,"cbid":307,"correlation":2308}},{"ph":"s","id":2308,"pid":912,"tid":912,"ts":3147904769723.525,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":0,"tid":7,"ts":3147904769768.208,"dur":0.864,"args":{"External id":10,"queued":0,"device":0,"context":1,"stream":7,"correlation":2311,"registers per thread":24,"shared memory":2,"blocks per SM":0.011905,"warps per SM":0.02381,"grid":[1,1,1],"block":[64,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"WARPS|BLOCKS","blockLimitRegs":42,"blockLimitSharedMem":88,"blockLimitWarps":24,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1536,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2311,"pid":0,"tid":7,"ts":3147904769768.208,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904769760.568,"dur":6.445,"args":{"External id":10,"cbid":307,"correlation":2311}},{"ph":"s","id":2311,"pid":912,"tid":912,"ts":3147904769760.568,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":912,"tid":912,"ts":3147904769965.553,"dur":0.615,"args":{"External id":18,"cbid":200,"correlation":2329}},{"ph":"f","id":2329,"pid":912,"tid":912,"ts":3147904769965.553,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":912,"tid":912,"ts":3147904769968.032,"dur":0.302,"args":{"External id":18,"cbid":51,"correlation":2332}},{"ph":"s","id":2332,"pid":912,"tid":912,"ts":3147904769968.032,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3147904769978.161,"dur":13.856,"args":{"External id":18,"queued":0,"device":0,"context":1,"stream":7,"correlation":2333,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2333,"pid":0,"tid":7,"ts":3147904769978.161,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904769968.592,"dur":8.905,"args":{"External id":18,"cbid":307,"correlation":2333}},{"ph":"s","id":2333,"pid":912,"tid":912,"ts":3147904769968.592,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":0,"tid":7,"ts":3147904770040.306,"dur":2.656,"args":{"External id":19,"queued":0,"device":0,"context":1,"stream":7,"correlation":2358,"registers per thread":40,"shared memory":64,"blocks per SM":0.761905,"warps per SM":6.095238,"grid":[64,1,1],"block":[256,1,1],"est. achieved occupancy %":13,"occupancy":{"activeBlocksPerMultiprocessor":6,"limitingFactors":"WARPS|REGS","blockLimitRegs":6,"blockLimitSharedMem":88,"blockLimitWarps":6,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":10240,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2358,"pid":0,"tid":7,"ts":3147904770040.306,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770031.489,"dur":7.816,"args":{"External id":19,"cbid":307,"correlation":2358}},{"ph":"s","id":2358,"pid":912,"tid":912,"ts":3147904770031.489,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":0,"tid":7,"ts":3147904770072.05,"dur":0.928,"args":{"External id":20,"queued":0,"device":0,"context":1,"stream":7,"correlation":2361,"registers per thread":24,"shared memory":2,"blocks per SM":0.011905,"warps per SM":0.02381,"grid":[1,1,1],"block":[64,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"WARPS|BLOCKS","blockLimitRegs":42,"blockLimitSharedMem":88,"blockLimitWarps":24,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1536,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2361,"pid":0,"tid":7,"ts":3147904770072.05,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770064.452,"dur":6.169,"args":{"External id":20,"cbid":307,"correlation":2361}},{"ph":"s","id":2361,"pid":912,"tid":912,"ts":3147904770064.452,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":912,"tid":912,"ts":3147904770260.897,"dur":0.631,"args":{"External id":28,"cbid":200,"correlation":2379}},{"ph":"f","id":2379,"pid":912,"tid":912,"ts":3147904770260.897,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":912,"tid":912,"ts":3147904770263.354,"dur":0.319,"args":{"External id":28,"cbid":51,"correlation":2382}},{"ph":"s","id":2382,"pid":912,"tid":912,"ts":3147904770263.354,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3147904770273.235,"dur":13.888,"args":{"External id":28,"queued":0,"device":0,"context":1,"stream":7,"correlation":2383,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2383,"pid":0,"tid":7,"ts":3147904770273.235,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770263.908,"dur":8.567,"args":{"External id":28,"cbid":307,"correlation":2383}},{"ph":"s","id":2383,"pid":912,"tid":912,"ts":3147904770263.908,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":0,"tid":7,"ts":3147904770333.523,"dur":2.656,"args":{"External id":29,"queued":0,"device":0,"context":1,"stream":7,"correlation":2408,"registers per thread":40,"shared memory":64,"blocks per SM":0.761905,"warps per SM":6.095238,"grid":[64,1,1],"block":[256,1,1],"est. achieved occupancy %":13,"occupancy":{"activeBlocksPerMultiprocessor":6,"limitingFactors":"WARPS|REGS","blockLimitRegs":6,"blockLimitSharedMem":88,"blockLimitWarps":6,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":10240,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2408,"pid":0,"tid":7,"ts":3147904770333.523,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770325.096,"dur":7.453,"args":{"External id":29,"cbid":307,"correlation":2408}},{"ph":"s","id":2408,"pid":912,"tid":912,"ts":3147904770325.096,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":0,"tid":7,"ts":3147904770365.075,"dur":0.928,"args":{"External id":30,"queued":0,"device":0,"context":1,"stream":7,"correlation":2411,"registers per thread":24,"shared memory":2,"blocks per SM":0.011905,"warps per SM":0.02381,"grid":[1,1,1],"block":[64,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"WARPS|BLOCKS","blockLimitRegs":42,"blockLimitSharedMem":88,"blockLimitWarps":24,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1536,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2411,"pid":0,"tid":7,"ts":3147904770365.075,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770357.342,"dur":6.251,"args":{"External id":30,"cbid":307,"correlation":2411}},{"ph":"s","id":2411,"pid":912,"tid":912,"ts":3147904770357.342,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":912,"tid":912,"ts":3147904770553.515,"dur":0.615,"args":{"External id":38,"cbid":200,"correlation":2429}},{"ph":"f","id":2429,"pid":912,"tid":912,"ts":3147904770553.515,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":912,"tid":912,"ts":3147904770555.911,"dur":0.332,"args":{"External id":38,"cbid":51,"correlation":2432}},{"ph":"s","id":2432,"pid":912,"tid":912,"ts":3147904770555.911,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3147904770565.748,"dur":13.888,"args":{"External id":38,"queued":0,"device":0,"context":1,"stream":7,"correlation":2433,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2433,"pid":0,"tid":7,"ts":3147904770565.748,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770556.479,"dur":8.538,"args":{"External id":38,"cbid":307,"correlation":2433}},{"ph":"s","id":2433,"pid":912,"tid":912,"ts":3147904770556.479,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":0,"tid":7,"ts":3147904770622.517,"dur":2.656,"args":{"External id":39,"queued":0,"device":0,"context":1,"stream":7,"correlation":2458,"registers per thread":40,"shared memory":64,"blocks per SM":0.761905,"warps per SM":6.095238,"grid":[64,1,1],"block":[256,1,1],"est. achieved occupancy %":13,"occupancy":{"activeBlocksPerMultiprocessor":6,"limitingFactors":"WARPS|REGS","blockLimitRegs":6,"blockLimitSharedMem":88,"blockLimitWarps":6,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":10240,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2458,"pid":0,"tid":7,"ts":3147904770622.517,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770614.004,"dur":7.666,"args":{"External id":39,"cbid":307,"correlation":2458}},{"ph":"s","id":2458,"pid":912,"tid":912,"ts":3147904770614.004,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":0,"tid":7,"ts":3147904770652.661,"dur":0.928,"args":{"External id":40,"queued":0,"device":0,"context":1,"stream":7,"correlation":2461,"registers per thread":24,"shared memory":2,"blocks per SM":0.011905,"warps per SM":0.02381,"grid":[1,1,1],"block":[64,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"WARPS|BLOCKS","blockLimitRegs":42,"blockLimitSharedMem":88,"blockLimitWarps":24,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1536,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2461,"pid":0,"tid":7,"ts":3147904770652.661,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770645.229,"dur":6.02,"args":{"External id":40,"cbid":307,"correlation":2461}},{"ph":"s","id":2461,"pid":912,"tid":912,"ts":3147904770645.229,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":912,"tid":912,"ts":3147904770889.726,"dur":0.627,"args":{"External id":48,"cbid":200,"correlation":2479}},{"ph":"f","id":2479,"pid":912,"tid":912,"ts":3147904770889.726,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":912,"tid":912,"ts":3147904770892.175,"dur":0.329,"args":{"External id":48,"cbid":51,"correlation":2482}},{"ph":"s","id":2482,"pid":912,"tid":912,"ts":3147904770892.175,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3147904770902.038,"dur":13.984,"args":{"External id":48,"queued":0,"device":0,"context":1,"stream":7,"correlation":2483,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2483,"pid":0,"tid":7,"ts":3147904770902.038,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770892.746,"dur":8.432,"args":{"External id":48,"cbid":307,"correlation":2483}},{"ph":"s","id":2483,"pid":912,"tid":912,"ts":3147904770892.746,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_red_fused__softmax_exp_mul_prepare_softmax_online_sub_sum_0","pid":0,"tid":7,"ts":3147904770958.327,"dur":2.656,"args":{"External id":49,"queued":0,"device":0,"context":1,"stream":7,"correlation":2508,"registers per thread":40,"shared memory":64,"blocks per SM":0.761905,"warps per SM":6.095238,"grid":[64,1,1],"block":[256,1,1],"est. achieved occupancy %":13,"occupancy":{"activeBlocksPerMultiprocessor":6,"limitingFactors":"WARPS|REGS","blockLimitRegs":6,"blockLimitSharedMem":88,"blockLimitWarps":6,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":10240,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2508,"pid":0,"tid":7,"ts":3147904770958.327,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770949.866,"dur":7.273,"args":{"External id":49,"cbid":307,"correlation":2508}},{"ph":"s","id":2508,"pid":912,"tid":912,"ts":3147904770949.866,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"triton_per_fused__assert_async_abs_all_le_sub_1","pid":0,"tid":7,"ts":3147904770992.311,"dur":0.896,"args":{"External id":50,"queued":0,"device":0,"context":1,"stream":7,"correlation":2511,"registers per thread":24,"shared memory":2,"blocks per SM":0.011905,"warps per SM":0.02381,"grid":[1,1,1],"block":[64,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"WARPS|BLOCKS","blockLimitRegs":42,"blockLimitSharedMem":88,"blockLimitWarps":24,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1536,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2511,"pid":0,"tid":7,"ts":3147904770992.311,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":912,"tid":912,"ts":3147904770984.647,"dur":6.306,"args":{"External id":50,"cbid":307,"correlation":2511}},{"ph":"s","id":2511,"pid":912,"tid":912,"ts":3147904770984.647,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceSynchronize","pid":912,"tid":912,"ts":3147904771078.462,"dur":6.536,"args":{"cbid":165,"correlation":2515}},{"ph":"s","id":2515,"pid":912,"tid":912,"ts":3147904771078.462,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"gpu_user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":0,"tid":7,"ts":3147904770902.037,"dur":91.171,"args":{"External id":47}},{"ph":"X","cat":"gpu_user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":0,"tid":7,"ts":3147904770565.747,"dur":87.843,"args":{"External id":37}},{"ph":"X","cat":"gpu_user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":0,"tid":7,"ts":3147904770273.234,"dur":92.77,"args":{"External id":27}},{"ph":"X","cat":"gpu_user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":0,"tid":7,"ts":3147904769978.16,"dur":94.819,"args":{"External id":17}},{"ph":"X","cat":"gpu_user_annotation","name":"## Call CompiledFxGraph famcgwtrcwdkgmnvfgg5cebbok3kp5fpkyzqaeve5yiqs3uy4a5p ##","pid":0,"tid":7,"ts":3147904769641.966,"dur":127.107,"args":{"External id":7}},{"ph":"X","cat":"Trace","name":"PyTorch Profiler (0)","pid":"Spans","tid":"PyTorch Profiler","ts":3147904769204.894,"dur":1885.763,"args":{"Op count":0}},{"ph":"M","name":"process_sort_index","ts":3147904769204.894,"pid":"Spans","tid":0,"args":{"sort_index":536870912}},{"ph":"i","s":"g","name":"Iteration Start: PyTorch Profiler","pid":"Traces","tid":"Trace PyTorch Profiler","ts":3147904769204.894},{"ph":"i","s":"g","name":"Record Window End","pid":"","tid":"","ts":3147904771271.453}],"traceName":"assert_async_compiled_trace.json"}