LLM: CPU benchmark using tcmalloc (#10675)

python/llm/dev/benchmark/all-in-one/run-deepspeed-spr.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-source ipex-llm-init
+source ipex-llm-init -t
 unset OMP_NUM_THREADS # deepspeed will set it for each instance automatically
 source /opt/intel/oneccl/env/setvars.sh
 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib

python/llm/dev/benchmark/all-in-one/run-hbm.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-source ipex-llm-init
+source ipex-llm-init -t
 
 sockets_num=$(lscpu | grep "Socket(s)" | awk -F ':' '{print $2}')
 cores_per_socket=$(lscpu | grep "Core(s) per socket" | awk -F ':' '{print $2}')

python/llm/dev/benchmark/all-in-one/run-spr.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-source ipex-llm-init
+source ipex-llm-init -t
 export OMP_NUM_THREADS=48
 
 # set following parameters according to the actual specs of the test machine