gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: isolate simulator predictor cache

Browse Source
This commit is contained in:
Gahow Wang
2026-07-20 18:11:33 +08:00
parent f727cbcf76
commit 157bf3668d
3 changed files with 44 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
runs/frontier-workload-regime-taxonomy-v0/jobs_simulator_v4.toml Normal file
View File

@@ -0,0 +1,33 @@
version = 1
[[jobs]]
name = "workload-regime-sim-tp1-v4-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash1"]
command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 1 both"
artifacts = []
[[jobs]]
name = "workload-regime-sim-tp2-v4-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash2"]
command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 2 both"
artifacts = []
[[jobs]]
name = "workload-regime-sim-tp4-noprefix-v4-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash3"]
command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 4 false"
artifacts = []
[[jobs]]
name = "workload-regime-sim-tp4-prefix-v4-20260720"
gpus = 1
gpu_model = "H20"
hosts = ["dash4"]
command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 4 true"
artifacts = []

5
runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh
View File

@@ -22,8 +22,9 @@ REPLAYSERVE_ROOT="${REPLAYSERVE_ROOT:-/home/admin/cpfs/wjh/replayserve}"
PROFILE_ROOT="${PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/aituner-graph-piecewise-bdc357d/runs/frontier-fidelity-envelope-v1/profiles/profile-v4-trace-final}"
KERNEL_PROFILE_ROOT="${KERNEL_PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/graph-piecewise-qwen30-20260717/full/frozen-kernel-only}"
ALLREDUCE_CSV="${ALLREDUCE_CSV:-/home/admin/cpfs/wjh/aituner/aituner-graph-piecewise-bdc357d/runs/frontier-fidelity-envelope-v1/profiles/measured-allreduce.csv}"
CUSTOM_PYTHON_DEPS="${CUSTOM_PYTHON_DEPS:-${EXPERIMENT_ROOT}/python-deps}"
CUSTOM_PYTHON_DEPS="${CUSTOM_PYTHON_DEPS:-${EXPERIMENT_ROOT}/python-deps-v2}"
BASE_PYTHON_DEPS="${BASE_PYTHON_DEPS:-/home/admin/cpfs/wjh/venvs/qwen36-vllm-0.20.2/lib/python3.12/site-packages}"
SIM_GENERATION="${SIM_GENERATION:-v4}"
RUNNER="${CHECKOUT}/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py"
for path in "${TRACES_ROOT}/manifest.json" "${FRONTIER_SOURCE}" \
@@ -36,7 +37,7 @@ done
run_mode() {
local prefix_mode="$1" output_root prefix_flag family
local -a families traces configs command
output_root="${EXPERIMENT_ROOT}/sim/tp${TP}-prefix-${prefix_mode}"
output_root="${EXPERIMENT_ROOT}/sim-${SIM_GENERATION}/tp${TP}-prefix-${prefix_mode}"
mkdir -p "${output_root}/provenance"
if [[ "${prefix_mode}" == "true" ]]; then