525 lines
26 KiB
JSON
525 lines
26 KiB
JSON
{
|
|
"cc_cache": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
|
"cells": {
|
|
"tp1_mns16": {
|
|
"argv": [
|
|
"/usr/bin/python3",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
|
"--simulation_mode",
|
|
"online",
|
|
"--sys_arch",
|
|
"co-location",
|
|
"--cc_backend_config_type",
|
|
"vidur",
|
|
"--cluster_config_num_replicas",
|
|
"1",
|
|
"--cluster_scheduler_config_type",
|
|
"sticky_round_robin",
|
|
"--replica_config_model_name",
|
|
"qwen3-a3b-30b-moe",
|
|
"--replica_config_device",
|
|
"h20",
|
|
"--replica_config_network_device",
|
|
"h20_dgx",
|
|
"--replica_config_attn_tensor_parallel_size",
|
|
"1",
|
|
"--replica_config_attn_data_parallel_size",
|
|
"1",
|
|
"--replica_config_moe_tensor_parallel_size",
|
|
"1",
|
|
"--replica_config_moe_expert_parallel_size",
|
|
"1",
|
|
"--replica_config_num_pipeline_stages",
|
|
"1",
|
|
"--replica_scheduler_config_type",
|
|
"vllm_v1",
|
|
"--decode_cuda_graph_mode",
|
|
"piecewise",
|
|
"--vllm_v1_scheduler_config_batch_size_cap",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
|
"8192",
|
|
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
|
"0",
|
|
"--vllm_v1_scheduler_config_block_size",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_num_blocks_mode",
|
|
"explicit",
|
|
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
|
"0.92",
|
|
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
|
"0",
|
|
"--request_generator_config_type",
|
|
"trace_replay",
|
|
"--trace_request_generator_config_trace_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp1-frontier.csv",
|
|
"--trace_request_generator_config_max_tokens",
|
|
"40960",
|
|
"--metrics_config_output_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp1_mns16/metrics",
|
|
"--metrics_config_run_id",
|
|
"joint_tp1_mns16",
|
|
"--metrics_config_write_metrics",
|
|
"--metrics_config_store_request_metrics",
|
|
"--metrics_config_store_batch_metrics",
|
|
"--metrics_config_store_token_completion_metrics",
|
|
"--metrics_config_store_utilization_metrics",
|
|
"--no-metrics_config_store_plots",
|
|
"--no-metrics_config_enable_chrome_trace",
|
|
"--no-metrics_config_write_json_trace",
|
|
"--metrics_config_store_frontier_stage_batch_ledger",
|
|
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
|
"8192",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
|
"32",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
|
"40960",
|
|
"--random_forrest_execution_time_predictor_config_no_cache",
|
|
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
|
"--vllm_v1_scheduler_config_num_blocks",
|
|
"20128",
|
|
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
|
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
|
"4",
|
|
"--cudagraph_capture_sizes",
|
|
"1",
|
|
"2",
|
|
"4",
|
|
"8",
|
|
"16",
|
|
"24",
|
|
"32",
|
|
"--vidur_cc_backend_config_all_reduce_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
|
"--vidur_cc_backend_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
|
"--vidur_cc_backend_config_k_fold_cv_splits",
|
|
"6",
|
|
"--vidur_cc_backend_config_num_training_job_threads",
|
|
"1",
|
|
"--metrics_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
|
],
|
|
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp1_mns16.log",
|
|
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp1_mns16/tp1/command.json",
|
|
"source_command_sha256": "a9815797b1601bf6f6cdf0269e84acb376a84945609e338868dc8347aab650e6",
|
|
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp1_mns16.json"
|
|
},
|
|
"tp2_mns16": {
|
|
"argv": [
|
|
"/usr/bin/python3",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
|
"--simulation_mode",
|
|
"online",
|
|
"--sys_arch",
|
|
"co-location",
|
|
"--cc_backend_config_type",
|
|
"vidur",
|
|
"--cluster_config_num_replicas",
|
|
"1",
|
|
"--cluster_scheduler_config_type",
|
|
"sticky_round_robin",
|
|
"--replica_config_model_name",
|
|
"qwen3-a3b-30b-moe",
|
|
"--replica_config_device",
|
|
"h20",
|
|
"--replica_config_network_device",
|
|
"h20_dgx",
|
|
"--replica_config_attn_tensor_parallel_size",
|
|
"2",
|
|
"--replica_config_attn_data_parallel_size",
|
|
"1",
|
|
"--replica_config_moe_tensor_parallel_size",
|
|
"2",
|
|
"--replica_config_moe_expert_parallel_size",
|
|
"1",
|
|
"--replica_config_num_pipeline_stages",
|
|
"1",
|
|
"--replica_scheduler_config_type",
|
|
"vllm_v1",
|
|
"--decode_cuda_graph_mode",
|
|
"piecewise",
|
|
"--vllm_v1_scheduler_config_batch_size_cap",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
|
"8192",
|
|
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
|
"0",
|
|
"--vllm_v1_scheduler_config_block_size",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_num_blocks_mode",
|
|
"explicit",
|
|
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
|
"0.92",
|
|
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
|
"0",
|
|
"--request_generator_config_type",
|
|
"trace_replay",
|
|
"--trace_request_generator_config_trace_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp2-frontier.csv",
|
|
"--trace_request_generator_config_max_tokens",
|
|
"40960",
|
|
"--metrics_config_output_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp2_mns16/metrics",
|
|
"--metrics_config_run_id",
|
|
"joint_tp2_mns16",
|
|
"--metrics_config_write_metrics",
|
|
"--metrics_config_store_request_metrics",
|
|
"--metrics_config_store_batch_metrics",
|
|
"--metrics_config_store_token_completion_metrics",
|
|
"--metrics_config_store_utilization_metrics",
|
|
"--no-metrics_config_store_plots",
|
|
"--no-metrics_config_enable_chrome_trace",
|
|
"--no-metrics_config_write_json_trace",
|
|
"--metrics_config_store_frontier_stage_batch_ledger",
|
|
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
|
"8192",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
|
"32",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
|
"40960",
|
|
"--random_forrest_execution_time_predictor_config_no_cache",
|
|
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
|
"--vllm_v1_scheduler_config_num_blocks",
|
|
"76620",
|
|
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
|
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
|
"4",
|
|
"--cudagraph_capture_sizes",
|
|
"1",
|
|
"2",
|
|
"4",
|
|
"8",
|
|
"16",
|
|
"24",
|
|
"32",
|
|
"--vidur_cc_backend_config_all_reduce_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
|
"--vidur_cc_backend_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
|
"--vidur_cc_backend_config_k_fold_cv_splits",
|
|
"6",
|
|
"--vidur_cc_backend_config_num_training_job_threads",
|
|
"1",
|
|
"--metrics_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
|
],
|
|
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp2_mns16.log",
|
|
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp2_mns16/tp2/command.json",
|
|
"source_command_sha256": "61788a8810be301c9dbc006624aa19b6a932bc44d341b836861087833cffc3df",
|
|
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp2_mns16.json"
|
|
},
|
|
"tp4_mns16": {
|
|
"argv": [
|
|
"/usr/bin/python3",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
|
"--simulation_mode",
|
|
"online",
|
|
"--sys_arch",
|
|
"co-location",
|
|
"--cc_backend_config_type",
|
|
"vidur",
|
|
"--cluster_config_num_replicas",
|
|
"1",
|
|
"--cluster_scheduler_config_type",
|
|
"sticky_round_robin",
|
|
"--replica_config_model_name",
|
|
"qwen3-a3b-30b-moe",
|
|
"--replica_config_device",
|
|
"h20",
|
|
"--replica_config_network_device",
|
|
"h20_dgx",
|
|
"--replica_config_attn_tensor_parallel_size",
|
|
"4",
|
|
"--replica_config_attn_data_parallel_size",
|
|
"1",
|
|
"--replica_config_moe_tensor_parallel_size",
|
|
"4",
|
|
"--replica_config_moe_expert_parallel_size",
|
|
"1",
|
|
"--replica_config_num_pipeline_stages",
|
|
"1",
|
|
"--replica_scheduler_config_type",
|
|
"vllm_v1",
|
|
"--decode_cuda_graph_mode",
|
|
"piecewise",
|
|
"--vllm_v1_scheduler_config_batch_size_cap",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
|
"8192",
|
|
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
|
"0",
|
|
"--vllm_v1_scheduler_config_block_size",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_num_blocks_mode",
|
|
"explicit",
|
|
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
|
"0.92",
|
|
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
|
"0",
|
|
"--request_generator_config_type",
|
|
"trace_replay",
|
|
"--trace_request_generator_config_trace_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp4-frontier.csv",
|
|
"--trace_request_generator_config_max_tokens",
|
|
"40960",
|
|
"--metrics_config_output_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp4_mns16/metrics",
|
|
"--metrics_config_run_id",
|
|
"joint_tp4_mns16",
|
|
"--metrics_config_write_metrics",
|
|
"--metrics_config_store_request_metrics",
|
|
"--metrics_config_store_batch_metrics",
|
|
"--metrics_config_store_token_completion_metrics",
|
|
"--metrics_config_store_utilization_metrics",
|
|
"--no-metrics_config_store_plots",
|
|
"--no-metrics_config_enable_chrome_trace",
|
|
"--no-metrics_config_write_json_trace",
|
|
"--metrics_config_store_frontier_stage_batch_ledger",
|
|
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
|
"8192",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
|
"32",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
|
"40960",
|
|
"--random_forrest_execution_time_predictor_config_no_cache",
|
|
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
|
"--vllm_v1_scheduler_config_num_blocks",
|
|
"191882",
|
|
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
|
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
|
"4",
|
|
"--cudagraph_capture_sizes",
|
|
"1",
|
|
"2",
|
|
"4",
|
|
"8",
|
|
"16",
|
|
"24",
|
|
"32",
|
|
"--vidur_cc_backend_config_all_reduce_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
|
"--vidur_cc_backend_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
|
"--vidur_cc_backend_config_k_fold_cv_splits",
|
|
"6",
|
|
"--vidur_cc_backend_config_num_training_job_threads",
|
|
"1",
|
|
"--metrics_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
|
],
|
|
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp4_mns16.log",
|
|
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp4_mns16/tp4/command.json",
|
|
"source_command_sha256": "9bbcf10446336ba5885193f391dd628cd18ff64d91a51ebcd463ffd24be95532",
|
|
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp4_mns16.json"
|
|
},
|
|
"tp4_mns32": {
|
|
"argv": [
|
|
"/usr/bin/python3",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/run_frontier_with_curves.py",
|
|
"--simulation_mode",
|
|
"online",
|
|
"--sys_arch",
|
|
"co-location",
|
|
"--cc_backend_config_type",
|
|
"vidur",
|
|
"--cluster_config_num_replicas",
|
|
"1",
|
|
"--cluster_scheduler_config_type",
|
|
"sticky_round_robin",
|
|
"--replica_config_model_name",
|
|
"qwen3-a3b-30b-moe",
|
|
"--replica_config_device",
|
|
"h20",
|
|
"--replica_config_network_device",
|
|
"h20_dgx",
|
|
"--replica_config_attn_tensor_parallel_size",
|
|
"4",
|
|
"--replica_config_attn_data_parallel_size",
|
|
"1",
|
|
"--replica_config_moe_tensor_parallel_size",
|
|
"4",
|
|
"--replica_config_moe_expert_parallel_size",
|
|
"1",
|
|
"--replica_config_num_pipeline_stages",
|
|
"1",
|
|
"--replica_scheduler_config_type",
|
|
"vllm_v1",
|
|
"--decode_cuda_graph_mode",
|
|
"piecewise",
|
|
"--vllm_v1_scheduler_config_batch_size_cap",
|
|
"32",
|
|
"--vllm_v1_scheduler_config_max_tokens_in_batch",
|
|
"8192",
|
|
"--vllm_v1_scheduler_config_long_prefill_token_threshold",
|
|
"0",
|
|
"--vllm_v1_scheduler_config_block_size",
|
|
"16",
|
|
"--vllm_v1_scheduler_config_num_blocks_mode",
|
|
"explicit",
|
|
"--vllm_v1_scheduler_config_gpu_memory_utilization",
|
|
"0.92",
|
|
"--vllm_v1_scheduler_config_non_kv_cache_overhead_bytes",
|
|
"0",
|
|
"--request_generator_config_type",
|
|
"trace_replay",
|
|
"--trace_request_generator_config_trace_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp4-frontier.csv",
|
|
"--trace_request_generator_config_max_tokens",
|
|
"40960",
|
|
"--metrics_config_output_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/sim/tp4_mns32/metrics",
|
|
"--metrics_config_run_id",
|
|
"joint_tp4_mns32",
|
|
"--metrics_config_write_metrics",
|
|
"--metrics_config_store_request_metrics",
|
|
"--metrics_config_store_batch_metrics",
|
|
"--metrics_config_store_token_completion_metrics",
|
|
"--metrics_config_store_utilization_metrics",
|
|
"--no-metrics_config_store_plots",
|
|
"--no-metrics_config_enable_chrome_trace",
|
|
"--no-metrics_config_write_json_trace",
|
|
"--metrics_config_store_frontier_stage_batch_ledger",
|
|
"--no-random_forrest_execution_time_predictor_config_enable_dummy_mode",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/profile-v4-trace-final/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_linear_op_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/linear_op.csv",
|
|
"--random_forrest_execution_time_predictor_config_atten_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/attention.csv",
|
|
"--random_forrest_execution_time_predictor_config_moe_kernel_only_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/frozen-kernel-only/moe.csv",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_prefill_chunk_size",
|
|
"8192",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_batch_size",
|
|
"64",
|
|
"--random_forrest_execution_time_predictor_config_prediction_max_tokens_per_request",
|
|
"40960",
|
|
"--random_forrest_execution_time_predictor_config_no_cache",
|
|
"--random_forrest_execution_time_predictor_config_skip_cpu_overhead_modeling",
|
|
"--vllm_v1_scheduler_config_num_blocks",
|
|
"191786",
|
|
"--vllm_v1_scheduler_config_enable_chunked_prefill",
|
|
"--random_forrest_execution_time_predictor_config_num_training_job_threads",
|
|
"4",
|
|
"--cudagraph_capture_sizes",
|
|
"1",
|
|
"2",
|
|
"4",
|
|
"8",
|
|
"16",
|
|
"24",
|
|
"32",
|
|
"40",
|
|
"48",
|
|
"56",
|
|
"64",
|
|
"--vidur_cc_backend_config_all_reduce_input_file",
|
|
"/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-profiles/measured-allreduce.csv",
|
|
"--vidur_cc_backend_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/cc-cache",
|
|
"--vidur_cc_backend_config_k_fold_cv_splits",
|
|
"6",
|
|
"--vidur_cc_backend_config_num_training_job_threads",
|
|
"1",
|
|
"--metrics_config_cache_dir",
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache"
|
|
],
|
|
"log": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/logs/tp4_mns32.log",
|
|
"source_command": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp4_mns32/tp4/command.json",
|
|
"source_command_sha256": "fbc7dee55590b415ed1cde8072de835ed155a0c20ba0eb305c3cb22aa8065a51",
|
|
"usage": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/usage/tp4_mns32.json"
|
|
}
|
|
},
|
|
"collective_curve": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/results/collective-curve.json",
|
|
"collective_curve_sha256": "f9543649d4ea78f08240bf1284ab74083aa5cf5671ed47e386047f1453300b36",
|
|
"collective_curve_variant": "drop_mean",
|
|
"frontier_checkout": "/tmp/frontier-attn-structured-v0",
|
|
"frontier_commit": "1f8900a4ac64e45754b03d0aa7c1dddab65785cf",
|
|
"mode": "joint",
|
|
"model_cache": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/model-cache",
|
|
"moe_curve": "/home/gahow/phd/aituner/runs/frontier-fused-moe-profile-v0/results/fused-moe-curve.json",
|
|
"moe_curve_sha256": "b94d65d9d581adefcc6c14ed4920cce6a1136f74f1014737dc3e4249bc8250d2",
|
|
"python": "/usr/bin/python3",
|
|
"python_dependency_roots": [
|
|
"/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/python-deps",
|
|
"/home/gahow/.cache/uv/archive-v0/-_kzErLcPO5nASZFX8b9k",
|
|
"/home/gahow/.cache/uv/archive-v0/FbaBs_QJ9QKEbQ9V_4aIR",
|
|
"/home/gahow/.cache/uv/archive-v0/fuHsGXD0Lv_UjFC8yI4-7",
|
|
"/home/gahow/.cache/uv/archive-v0/jFGdqQLpB1eopfm9VxT3j",
|
|
"/home/gahow/.cache/uv/archive-v0/YWW6ExSJuPVvv4-qYQTin",
|
|
"/home/gahow/.cache/uv/archive-v0/3_qxZ5Ll-EpVAGZfbksfe"
|
|
],
|
|
"traces": {
|
|
"1": {
|
|
"first_arrival_s": 0.0,
|
|
"last_arrival_s": 595.348837209302,
|
|
"requests": 129,
|
|
"source_request_metrics": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp1_mns16/tp1/metrics/qwen3_a3b_30b_moe/online_serving/qwen30_trace_tp1_mns16_tp1/request_metrics.csv",
|
|
"source_sha256": "0b82e09644a5884fcd10d894b68495daefdabb32b770146c2f9ece37b8469f4f",
|
|
"trace": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp1-frontier.csv",
|
|
"trace_sha256": "59dd8996ff879ef94330004104dfdf515b791bce4036576eccc93290e9206dad"
|
|
},
|
|
"2": {
|
|
"first_arrival_s": 0.0,
|
|
"last_arrival_s": 297.674418604651,
|
|
"requests": 129,
|
|
"source_request_metrics": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp2_mns16/tp2/metrics/qwen3_a3b_30b_moe/online_serving/qwen30_trace_tp2_mns16_tp2/request_metrics.csv",
|
|
"source_sha256": "33983081bb20dd5e2053e9e3d13def8732e958150c9b47a8609ba345123f2316",
|
|
"trace": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp2-frontier.csv",
|
|
"trace_sha256": "64fc077b38274a76a8279884ac4115836cd1157c95119c64fabac50d81124f69"
|
|
},
|
|
"4": {
|
|
"first_arrival_s": 0.0,
|
|
"last_arrival_s": 148.837209302326,
|
|
"requests": 129,
|
|
"source_request_metrics": "/home/gahow/phd/aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-lo-fixed-pd-cells/sim/fixed-pd/runs/tp4_mns16/tp4/metrics/qwen3_a3b_30b_moe/online_serving/qwen30_trace_tp4_mns16_tp4/request_metrics.csv",
|
|
"source_sha256": "b36cd383c07b546d2c1f2fac754d5dbb92efd6880316b4233a7aef9fa1115a36",
|
|
"trace": "/home/gahow/phd/aituner/runs/frontier-collective-joint-v0/counterfactual/joint-r2/inputs/tp4-frontier.csv",
|
|
"trace_sha256": "adb3d6f3932a44c86c3d9e7cf1e57739594e8c48d19a26b5aa54b37dce0e0c19"
|
|
}
|
|
}
|
|
} |