Add prospective active intervention experiment

This commit is contained in:
2026-07-15 02:03:38 +08:00
parent d229f2a85e
commit e5fd463f05
9 changed files with 1875 additions and 16 deletions

View File

@@ -453,11 +453,21 @@ def execute_session(
)
if float(state["gpu_hours_total"]) + projection > base.GPU_LIMIT:
raise RuntimeError(f"projected cost exceeds cap before {name}")
load_values = {
float(item["selection"]["offered_req_s_per_gpu"])
for item in manifest["repetitions"].values()
}
load_text = (
f"{next(iter(load_values)):.6g}"
if len(load_values) == 1
else ",".join(f"{value:.6g}" for value in sorted(load_values))
)
echo = (
f"ACTION_AWARE_SESSION_ECHO host=dash0 config={name} tp=4 "
f"mns={config['mns']} mbbt={config['mbbt']} gpus=0-3 "
f"workload={manifest['source']['window_id']} load_per_gpu=2.125 "
f"duration_s=300 repetitions={','.join(map(str, config['repetition_order']))} "
f"workload={manifest['source']['window_id']} load_per_gpu={load_text} "
f"duration_s={manifest['engine']['duration_s']} "
f"repetitions={','.join(map(str, config['repetition_order']))} "
f"source={args.manifest} output={args.run_root / 'sessions' / name} "
f"spent_h20h={state['gpu_hours_total']:.6f} "
f"remaining_projection_h20h={projection:.3f} cap_h20h={base.GPU_LIMIT:.1f}"