* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 293410 tid 293410 thread 0 bound to OS proc set {0}
OMP: pid 293410 tid 293478 thread 2 bound to OS proc set {32}
OMP: pid 293410 tid 293477 thread 1 bound to OS proc set {16}
OMP: pid 293410 tid 293479 thread 3 bound to OS proc set {48}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 4, "n_threads_batch": 4, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 15.744153, "speed_tg": 32.520008, "t": 15.744153, "speed": 32.520008}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_2 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 293547 tid 293547 thread 0 bound to OS proc set {0}
OMP: pid 293547 tid 293614 thread 1 bound to OS proc set {8}
OMP: pid 293547 tid 293616 thread 3 bound to OS proc set {24}
OMP: pid 293547 tid 293615 thread 2 bound to OS proc set {16}
OMP: pid 293547 tid 293617 thread 4 bound to OS proc set {32}
OMP: pid 293547 tid 293619 thread 6 bound to OS proc set {48}
OMP: pid 293547 tid 293618 thread 5 bound to OS proc set {40}
OMP: pid 293547 tid 293620 thread 7 bound to OS proc set {56}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 8, "n_threads_batch": 8, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000001, "speed_pp": 0.000000, "t_tg": 8.426284, "speed_tg": 60.762253, "t": 8.426285, "speed": 60.762249}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_3 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 293640 tid 293640 thread 0 bound to OS proc set {0}
OMP: pid 293640 tid 293707 thread 1 bound to OS proc set {4}
OMP: pid 293640 tid 293708 thread 2 bound to OS proc set {8}
OMP: pid 293640 tid 293718 thread 12 bound to OS proc set {48}
OMP: pid 293640 tid 293709 thread 3 bound to OS proc set {12}
OMP: pid 293640 tid 293720 thread 14 bound to OS proc set {56}
OMP: pid 293640 tid 293712 thread 6 bound to OS proc set {24}
OMP: pid 293640 tid 293719 thread 13 bound to OS proc set {52}
OMP: pid 293640 tid 293713 thread 7 bound to OS proc set {28}
OMP: pid 293640 tid 293717 thread 11 bound to OS proc set {44}
OMP: pid 293640 tid 293714 thread 8 bound to OS proc set {32}
OMP: pid 293640 tid 293711 thread 5 bound to OS proc set {20}
OMP: pid 293640 tid 293716 thread 10 bound to OS proc set {40}
OMP: pid 293640 tid 293715 thread 9 bound to OS proc set {36}
OMP: pid 293640 tid 293710 thread 4 bound to OS proc set {16}
OMP: pid 293640 tid 293721 thread 15 bound to OS proc set {60}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 16, "n_threads_batch": 16, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000001, "speed_pp": 0.000000, "t_tg": 4.872815, "speed_tg": 105.072731, "t": 4.872816, "speed": 105.072708}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_4 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 293742 tid 293742 thread 0 bound to OS proc set {0}
OMP: pid 293742 tid 293809 thread 1 bound to OS proc set {2}
OMP: pid 293742 tid 293811 thread 3 bound to OS proc set {8}
OMP: pid 293742 tid 293820 thread 12 bound to OS proc set {32}
OMP: pid 293742 tid 293814 thread 6 bound to OS proc set {16}
OMP: pid 293742 tid 293823 thread 15 bound to OS proc set {40}
OMP: pid 293742 tid 293812 thread 4 bound to OS proc set {10}
OMP: pid 293742 tid 293827 thread 19 bound to OS proc set {51}
OMP: pid 293742 tid 293824 thread 16 bound to OS proc set {43}
OMP: pid 293742 tid 293810 thread 2 bound to OS proc set {5}
OMP: pid 293742 tid 293815 thread 7 bound to OS proc set {18}
OMP: pid 293742 tid 293826 thread 18 bound to OS proc set {48}
OMP: pid 293742 tid 293822 thread 14 bound to OS proc set {37}
OMP: pid 293742 tid 293816 thread 8 bound to OS proc set {21}
OMP: pid 293742 tid 293813 thread 5 bound to OS proc set {13}
OMP: pid 293742 tid 293819 thread 11 bound to OS proc set {29}
OMP: pid 293742 tid 293817 thread 9 bound to OS proc set {24}
OMP: pid 293742 tid 293818 thread 10 bound to OS proc set {27}
OMP: pid 293742 tid 293821 thread 13 bound to OS proc set {35}
OMP: pid 293742 tid 293825 thread 17 bound to OS proc set {46}
OMP: pid 293742 tid 293828 thread 20 bound to OS proc set {54}
OMP: pid 293742 tid 293830 thread 22 bound to OS proc set {59}
OMP: pid 293742 tid 293829 thread 21 bound to OS proc set {56}
OMP: pid 293742 tid 293831 thread 23 bound to OS proc set {62}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 24, "n_threads_batch": 24, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 4.254328, "speed_tg": 120.348038, "t": 4.254328, "speed": 120.348038}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_5 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 293851 tid 293851 thread 0 bound to OS proc set {0}
OMP: pid 293851 tid 293918 thread 1 bound to OS proc set {2}
OMP: pid 293851 tid 293929 thread 12 bound to OS proc set {24}
OMP: pid 293851 tid 293925 thread 8 bound to OS proc set {16}
OMP: pid 293851 tid 293919 thread 2 bound to OS proc set {4}
OMP: pid 293851 tid 293924 thread 7 bound to OS proc set {14}
OMP: pid 293851 tid 293923 thread 6 bound to OS proc set {12}
OMP: pid 293851 tid 293921 thread 4 bound to OS proc set {8}
OMP: pid 293851 tid 293920 thread 3 bound to OS proc set {6}
OMP: pid 293851 tid 293926 thread 9 bound to OS proc set {18}
OMP: pid 293851 tid 293922 thread 5 bound to OS proc set {10}
OMP: pid 293851 tid 293927 thread 10 bound to OS proc set {20}
OMP: pid 293851 tid 293934 thread 17 bound to OS proc set {34}
OMP: pid 293851 tid 293932 thread 15 bound to OS proc set {30}
OMP: pid 293851 tid 293936 thread 19 bound to OS proc set {38}
OMP: pid 293851 tid 293933 thread 16 bound to OS proc set {32}
OMP: pid 293851 tid 293947 thread 30 bound to OS proc set {60}
OMP: pid 293851 tid 293928 thread 11 bound to OS proc set {22}
OMP: pid 293851 tid 293930 thread 13 bound to OS proc set {26}
OMP: pid 293851 tid 293944 thread 27 bound to OS proc set {54}
OMP: pid 293851 tid 293945 thread 28 bound to OS proc set {56}
OMP: pid 293851 tid 293948 thread 31 bound to OS proc set {62}
OMP: pid 293851 tid 293931 thread 14 bound to OS proc set {28}
OMP: pid 293851 tid 293941 thread 24 bound to OS proc set {48}
OMP: pid 293851 tid 293943 thread 26 bound to OS proc set {52}
OMP: pid 293851 tid 293946 thread 29 bound to OS proc set {58}
OMP: pid 293851 tid 293935 thread 18 bound to OS proc set {36}
OMP: pid 293851 tid 293937 thread 20 bound to OS proc set {40}
OMP: pid 293851 tid 293942 thread 25 bound to OS proc set {50}
OMP: pid 293851 tid 293940 thread 23 bound to OS proc set {46}
OMP: pid 293851 tid 293938 thread 21 bound to OS proc set {42}
OMP: pid 293851 tid 293939 thread 22 bound to OS proc set {44}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 32, "n_threads_batch": 32, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 4.047340, "speed_tg": 126.502838, "t": 4.047340, "speed": 126.502838}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_6 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 294016 tid 294016 thread 0 bound to OS proc set {0}
OMP: pid 294016 tid 294085 thread 3 bound to OS proc set {4}
OMP: pid 294016 tid 294083 thread 1 bound to OS proc set {1}
OMP: pid 294016 tid 294084 thread 2 bound to OS proc set {3}
OMP: pid 294016 tid 294097 thread 15 bound to OS proc set {24}
OMP: pid 294016 tid 294090 thread 8 bound to OS proc set {13}
OMP: pid 294016 tid 294096 thread 14 bound to OS proc set {22}
OMP: pid 294016 tid 294114 thread 32 bound to OS proc set {52}
OMP: pid 294016 tid 294092 thread 10 bound to OS proc set {16}
OMP: pid 294016 tid 294086 thread 4 bound to OS proc set {6}
OMP: pid 294016 tid 294089 thread 7 bound to OS proc set {11}
OMP: pid 294016 tid 294088 thread 6 bound to OS proc set {9}
OMP: pid 294016 tid 294118 thread 36 bound to OS proc set {58}
OMP: pid 294016 tid 294087 thread 5 bound to OS proc set {8}
OMP: pid 294016 tid 294117 thread 35 bound to OS proc set {56}
OMP: pid 294016 tid 294116 thread 34 bound to OS proc set {55}
OMP: pid 294016 tid 294093 thread 11 bound to OS proc set {17}
OMP: pid 294016 tid 294094 thread 12 bound to OS proc set {19}
OMP: pid 294016 tid 294120 thread 38 bound to OS proc set {61}
OMP: pid 294016 tid 294113 thread 31 bound to OS proc set {50}
OMP: pid 294016 tid 294110 thread 28 bound to OS proc set {45}
OMP: pid 294016 tid 294106 thread 24 bound to OS proc set {39}
OMP: pid 294016 tid 294121 thread 39 bound to OS proc set {63}
OMP: pid 294016 tid 294115 thread 33 bound to OS proc set {53}
OMP: pid 294016 tid 294101 thread 19 bound to OS proc set {30}
OMP: pid 294016 tid 294100 thread 18 bound to OS proc set {29}
OMP: pid 294016 tid 294119 thread 37 bound to OS proc set {60}
OMP: pid 294016 tid 294099 thread 17 bound to OS proc set {27}
OMP: pid 294016 tid 294112 thread 30 bound to OS proc set {48}
OMP: pid 294016 tid 294095 thread 13 bound to OS proc set {21}
OMP: pid 294016 tid 294109 thread 27 bound to OS proc set {43}
OMP: pid 294016 tid 294102 thread 20 bound to OS proc set {32}
OMP: pid 294016 tid 294111 thread 29 bound to OS proc set {47}
OMP: pid 294016 tid 294104 thread 22 bound to OS proc set {35}
OMP: pid 294016 tid 294103 thread 21 bound to OS proc set {34}
OMP: pid 294016 tid 294105 thread 23 bound to OS proc set {37}
OMP: pid 294016 tid 294098 thread 16 bound to OS proc set {26}
OMP: pid 294016 tid 294107 thread 25 bound to OS proc set {40}
OMP: pid 294016 tid 294091 thread 9 bound to OS proc set {14}
OMP: pid 294016 tid 294108 thread 26 bound to OS proc set {42}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 40, "n_threads_batch": 40, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.871297, "speed_tg": 132.255417, "t": 3.871297, "speed": 132.255417}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_7 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 294141 tid 294141 thread 0 bound to OS proc set {0}
OMP: pid 294141 tid 294209 thread 2 bound to OS proc set {2}
OMP: pid 294141 tid 294208 thread 1 bound to OS proc set {1}
OMP: pid 294141 tid 294219 thread 12 bound to OS proc set {16}
OMP: pid 294141 tid 294214 thread 7 bound to OS proc set {9}
OMP: pid 294141 tid 294242 thread 35 bound to OS proc set {47}
OMP: pid 294141 tid 294213 thread 6 bound to OS proc set {8}
OMP: pid 294141 tid 294211 thread 4 bound to OS proc set {5}
OMP: pid 294141 tid 294210 thread 3 bound to OS proc set {4}
OMP: pid 294141 tid 294220 thread 13 bound to OS proc set {17}
OMP: pid 294141 tid 294222 thread 15 bound to OS proc set {20}
OMP: pid 294141 tid 294217 thread 10 bound to OS proc set {13}
OMP: pid 294141 tid 294241 thread 34 bound to OS proc set {46}
OMP: pid 294141 tid 294218 thread 11 bound to OS proc set {14}
OMP: pid 294141 tid 294240 thread 33 bound to OS proc set {44}
OMP: pid 294141 tid 294221 thread 14 bound to OS proc set {18}
OMP: pid 294141 tid 294251 thread 44 bound to OS proc set {59}
OMP: pid 294141 tid 294223 thread 16 bound to OS proc set {21}
OMP: pid 294141 tid 294212 thread 5 bound to OS proc set {6}
OMP: pid 294141 tid 294253 thread 46 bound to OS proc set {62}
OMP: pid 294141 tid 294237 thread 30 bound to OS proc set {40}
OMP: pid 294141 tid 294238 thread 31 bound to OS proc set {41}
OMP: pid 294141 tid 294252 thread 45 bound to OS proc set {60}
OMP: pid 294141 tid 294233 thread 26 bound to OS proc set {35}
OMP: pid 294141 tid 294215 thread 8 bound to OS proc set {10}
OMP: pid 294141 tid 294227 thread 20 bound to OS proc set {27}
OMP: pid 294141 tid 294226 thread 19 bound to OS proc set {25}
OMP: pid 294141 tid 294235 thread 28 bound to OS proc set {37}
OMP: pid 294141 tid 294239 thread 32 bound to OS proc set {43}
OMP: pid 294141 tid 294250 thread 43 bound to OS proc set {58}
OMP: pid 294141 tid 294234 thread 27 bound to OS proc set {36}
OMP: pid 294141 tid 294225 thread 18 bound to OS proc set {24}
OMP: pid 294141 tid 294216 thread 9 bound to OS proc set {12}
OMP: pid 294141 tid 294231 thread 24 bound to OS proc set {32}
OMP: pid 294141 tid 294254 thread 47 bound to OS proc set {63}
OMP: pid 294141 tid 294243 thread 36 bound to OS proc set {48}
OMP: pid 294141 tid 294224 thread 17 bound to OS proc set {23}
OMP: pid 294141 tid 294228 thread 21 bound to OS proc set {28}
OMP: pid 294141 tid 294229 thread 22 bound to OS proc set {29}
OMP: pid 294141 tid 294236 thread 29 bound to OS proc set {39}
OMP: pid 294141 tid 294230 thread 23 bound to OS proc set {31}
OMP: pid 294141 tid 294247 thread 40 bound to OS proc set {54}
OMP: pid 294141 tid 294244 thread 37 bound to OS proc set {50}
OMP: pid 294141 tid 294232 thread 25 bound to OS proc set {33}
OMP: pid 294141 tid 294246 thread 39 bound to OS proc set {52}
OMP: pid 294141 tid 294248 thread 41 bound to OS proc set {55}
OMP: pid 294141 tid 294249 thread 42 bound to OS proc set {56}
OMP: pid 294141 tid 294245 thread 38 bound to OS proc set {51}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 48, "n_threads_batch": 48, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.836694, "speed_tg": 133.448227, "t": 3.836694, "speed": 133.448227}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_8 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 294275 tid 294275 thread 0 bound to OS proc set {0}
OMP: pid 294275 tid 294345 thread 3 bound to OS proc set {3}
OMP: pid 294275 tid 294354 thread 12 bound to OS proc set {13}
OMP: pid 294275 tid 294344 thread 2 bound to OS proc set {2}
OMP: pid 294275 tid 294343 thread 1 bound to OS proc set {1}
OMP: pid 294275 tid 294353 thread 11 bound to OS proc set {12}
OMP: pid 294275 tid 294346 thread 4 bound to OS proc set {4}
OMP: pid 294275 tid 294349 thread 7 bound to OS proc set {8}
OMP: pid 294275 tid 294350 thread 8 bound to OS proc set {9}
OMP: pid 294275 tid 294352 thread 10 bound to OS proc set {11}
OMP: pid 294275 tid 294351 thread 9 bound to OS proc set {10}
OMP: pid 294275 tid 294393 thread 51 bound to OS proc set {59}
OMP: pid 294275 tid 294355 thread 13 bound to OS proc set {15}
OMP: pid 294275 tid 294390 thread 48 bound to OS proc set {55}
OMP: pid 294275 tid 294356 thread 14 bound to OS proc set {16}
OMP: pid 294275 tid 294370 thread 28 bound to OS proc set {32}
OMP: pid 294275 tid 294389 thread 47 bound to OS proc set {54}
OMP: pid 294275 tid 294392 thread 50 bound to OS proc set {58}
OMP: pid 294275 tid 294357 thread 15 bound to OS proc set {17}
OMP: pid 294275 tid 294385 thread 43 bound to OS proc set {49}
OMP: pid 294275 tid 294382 thread 40 bound to OS proc set {46}
OMP: pid 294275 tid 294386 thread 44 bound to OS proc set {51}
OMP: pid 294275 tid 294373 thread 31 bound to OS proc set {35}
OMP: pid 294275 tid 294384 thread 42 bound to OS proc set {48}
OMP: pid 294275 tid 294381 thread 39 bound to OS proc set {45}
OMP: pid 294275 tid 294394 thread 52 bound to OS proc set {60}
OMP: pid 294275 tid 294391 thread 49 bound to OS proc set {56}
OMP: pid 294275 tid 294397 thread 55 bound to OS proc set {63}
OMP: pid 294275 tid 294369 thread 27 bound to OS proc set {31}
OMP: pid 294275 tid 294360 thread 18 bound to OS proc set {20}
OMP: pid 294275 tid 294388 thread 46 bound to OS proc set {53}
OMP: pid 294275 tid 294396 thread 54 bound to OS proc set {62}
OMP: pid 294275 tid 294348 thread 6 bound to OS proc set {6}
OMP: pid 294275 tid 294371 thread 29 bound to OS proc set {33}
OMP: pid 294275 tid 294374 thread 32 bound to OS proc set {37}
OMP: pid 294275 tid 294366 thread 24 bound to OS proc set {27}
OMP: pid 294275 tid 294358 thread 16 bound to OS proc set {18}
OMP: pid 294275 tid 294368 thread 26 bound to OS proc set {30}
OMP: pid 294275 tid 294378 thread 36 bound to OS proc set {41}
OMP: pid 294275 tid 294377 thread 35 bound to OS proc set {40}
OMP: pid 294275 tid 294372 thread 30 bound to OS proc set {34}
OMP: pid 294275 tid 294383 thread 41 bound to OS proc set {47}
OMP: pid 294275 tid 294387 thread 45 bound to OS proc set {52}
OMP: pid 294275 tid 294347 thread 5 bound to OS proc set {5}
OMP: pid 294275 tid 294367 thread 25 bound to OS proc set {29}
OMP: pid 294275 tid 294359 thread 17 bound to OS proc set {19}
OMP: pid 294275 tid 294376 thread 34 bound to OS proc set {39}
OMP: pid 294275 tid 294380 thread 38 bound to OS proc set {44}
OMP: pid 294275 tid 294379 thread 37 bound to OS proc set {42}
OMP: pid 294275 tid 294362 thread 20 bound to OS proc set {23}
OMP: pid 294275 tid 294364 thread 22 bound to OS proc set {25}
OMP: pid 294275 tid 294365 thread 23 bound to OS proc set {26}
OMP: pid 294275 tid 294363 thread 21 bound to OS proc set {24}
OMP: pid 294275 tid 294361 thread 19 bound to OS proc set {22}
OMP: pid 294275 tid 294375 thread 33 bound to OS proc set {38}
OMP: pid 294275 tid 294395 thread 53 bound to OS proc set {61}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 56, "n_threads_batch": 56, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.893043, "speed_tg": 131.516663, "t": 3.893043, "speed": 131.516663}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9
To display your profiling results:
#######################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#######################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_9 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 294418 tid 294418 thread 0 bound to OS proc set {0}
OMP: pid 294418 tid 294487 thread 3 bound to OS proc set {3}
OMP: pid 294418 tid 294486 thread 2 bound to OS proc set {2}
OMP: pid 294418 tid 294485 thread 1 bound to OS proc set {1}
OMP: pid 294418 tid 294488 thread 4 bound to OS proc set {4}
OMP: pid 294418 tid 294490 thread 6 bound to OS proc set {6}
OMP: pid 294418 tid 294496 thread 12 bound to OS proc set {12}
OMP: pid 294418 tid 294489 thread 5 bound to OS proc set {5}
OMP: pid 294418 tid 294535 thread 51 bound to OS proc set {51}
OMP: pid 294418 tid 294499 thread 15 bound to OS proc set {15}
OMP: pid 294418 tid 294495 thread 11 bound to OS proc set {11}
OMP: pid 294418 tid 294497 thread 13 bound to OS proc set {13}
OMP: pid 294418 tid 294500 thread 16 bound to OS proc set {16}
OMP: pid 294418 tid 294498 thread 14 bound to OS proc set {14}
OMP: pid 294418 tid 294533 thread 49 bound to OS proc set {49}
OMP: pid 294418 tid 294492 thread 8 bound to OS proc set {8}
OMP: pid 294418 tid 294503 thread 19 bound to OS proc set {19}
OMP: pid 294418 tid 294542 thread 58 bound to OS proc set {58}
OMP: pid 294418 tid 294545 thread 61 bound to OS proc set {61}
OMP: pid 294418 tid 294494 thread 10 bound to OS proc set {10}
OMP: pid 294418 tid 294491 thread 7 bound to OS proc set {7}
OMP: pid 294418 tid 294546 thread 62 bound to OS proc set {62}
OMP: pid 294418 tid 294534 thread 50 bound to OS proc set {50}
OMP: pid 294418 tid 294493 thread 9 bound to OS proc set {9}
OMP: pid 294418 tid 294501 thread 17 bound to OS proc set {17}
OMP: pid 294418 tid 294502 thread 18 bound to OS proc set {18}
OMP: pid 294418 tid 294514 thread 30 bound to OS proc set {30}
OMP: pid 294418 tid 294543 thread 59 bound to OS proc set {59}
OMP: pid 294418 tid 294539 thread 55 bound to OS proc set {55}
OMP: pid 294418 tid 294544 thread 60 bound to OS proc set {60}
OMP: pid 294418 tid 294516 thread 32 bound to OS proc set {32}
OMP: pid 294418 tid 294504 thread 20 bound to OS proc set {20}
OMP: pid 294418 tid 294518 thread 34 bound to OS proc set {34}
OMP: pid 294418 tid 294515 thread 31 bound to OS proc set {31}
OMP: pid 294418 tid 294532 thread 48 bound to OS proc set {48}
OMP: pid 294418 tid 294508 thread 24 bound to OS proc set {24}
OMP: pid 294418 tid 294531 thread 47 bound to OS proc set {47}
OMP: pid 294418 tid 294512 thread 28 bound to OS proc set {28}
OMP: pid 294418 tid 294530 thread 46 bound to OS proc set {46}
OMP: pid 294418 tid 294511 thread 27 bound to OS proc set {27}
OMP: pid 294418 tid 294541 thread 57 bound to OS proc set {57}
OMP: pid 294418 tid 294522 thread 38 bound to OS proc set {38}
OMP: pid 294418 tid 294510 thread 26 bound to OS proc set {26}
OMP: pid 294418 tid 294528 thread 44 bound to OS proc set {44}
OMP: pid 294418 tid 294538 thread 54 bound to OS proc set {54}
OMP: pid 294418 tid 294517 thread 33 bound to OS proc set {33}
OMP: pid 294418 tid 294519 thread 35 bound to OS proc set {35}
OMP: pid 294418 tid 294536 thread 52 bound to OS proc set {52}
OMP: pid 294418 tid 294509 thread 25 bound to OS proc set {25}
OMP: pid 294418 tid 294524 thread 40 bound to OS proc set {40}
OMP: pid 294418 tid 294507 thread 23 bound to OS proc set {23}
OMP: pid 294418 tid 294520 thread 36 bound to OS proc set {36}
OMP: pid 294418 tid 294540 thread 56 bound to OS proc set {56}
OMP: pid 294418 tid 294521 thread 37 bound to OS proc set {37}
OMP: pid 294418 tid 294505 thread 21 bound to OS proc set {21}
OMP: pid 294418 tid 294525 thread 41 bound to OS proc set {41}
OMP: pid 294418 tid 294537 thread 53 bound to OS proc set {53}
OMP: pid 294418 tid 294523 thread 39 bound to OS proc set {39}
OMP: pid 294418 tid 294529 thread 45 bound to OS proc set {45}
OMP: pid 294418 tid 294526 thread 42 bound to OS proc set {42}
OMP: pid 294418 tid 294527 thread 43 bound to OS proc set {43}
OMP: pid 294418 tid 294506 thread 22 bound to OS proc set {22}
OMP: pid 294418 tid 294513 thread 29 bound to OS proc set {29}
OMP: pid 294418 tid 294547 thread 63 bound to OS proc set {63}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 64, "n_threads_batch": 64, "pp": 0, "tg": 128, "pl": 4, "n_kv": 512, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 4.013564, "speed_tg": 127.567413, "t": 4.013564, "speed": 127.567413}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-406-4796/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_10-20-13/tools/lprof_npsu_run_10 #
########################################################################################################################################################################################################################################
