experiment: add per-gpu workload control

This commit is contained in:
2026-07-20 18:48:22 +08:00
parent a033a72195
commit 809ad9ffef
8 changed files with 330 additions and 7 deletions

View File

@@ -0,0 +1,33 @@
version = 1
[[jobs]]
name = "workload-regime-per-gpu-sim-tp1-v1-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash1"]
command = "TRACES_ROOT=/home/admin/cpfs/wjh/aituner/workload-regime-20260720/traces-per-gpu-low SIM_GENERATION=per-gpu-v1 bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 1 both"
artifacts = []
[[jobs]]
name = "workload-regime-per-gpu-sim-tp2-v1-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash2"]
command = "TRACES_ROOT=/home/admin/cpfs/wjh/aituner/workload-regime-20260720/traces-per-gpu-low SIM_GENERATION=per-gpu-v1 bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 2 both"
artifacts = []
[[jobs]]
name = "workload-regime-per-gpu-sim-tp4-noprefix-v1-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash3"]
command = "TRACES_ROOT=/home/admin/cpfs/wjh/aituner/workload-regime-20260720/traces-per-gpu-low SIM_GENERATION=per-gpu-v1 bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 4 false"
artifacts = []
[[jobs]]
name = "workload-regime-per-gpu-sim-tp4-prefix-v1-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash4"]
command = "TRACES_ROOT=/home/admin/cpfs/wjh/aituner/workload-regime-20260720/traces-per-gpu-low SIM_GENERATION=per-gpu-v1 bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 4 true"
artifacts = []