Implement bounded streaming CPU functional reuse pilot

functional/preflight.py

@@ -0,0 +1,27 @@
+"""One 8-token real text, bounded memory/semantic capacity smoke check."""
+import argparse
+import json
+from pathlib import Path
+import resource
+import time
+import numpy as np
+from .model import StreamingLM
+from .run import tokenize,write_json
+
+
+def main():
+    p=argparse.ArgumentParser();p.add_argument('--root',required=True,type=Path);a=p.parse_args()
+    samples,ids=tokenize(a.root)
+    start=time.time()
+    lm=StreamingLM(a.root/'weights',json.loads((a.root/'model_config.json').read_text()),seconds=1200)
+    def progress(layer):print(json.dumps({'preflight_layer':layer,'seconds':time.time()-start}),flush=True)
+    h,_=lm.forward(ids[:1,:8],progress=progress)
+    nll=lm.nll(h,ids[:1,:8])
+    if not np.isfinite(nll).all():raise FloatingPointError('Nonfinite NLL')
+    write_json(a.root/'preflight.json',{'passed':True,'sample_id':samples[0]['id'],'tokens':8,
+               'elapsed_seconds':time.time()-start,'peak_rss_kib':resource.getrusage(resource.RUSAGE_SELF).ru_maxrss,
+               'mean_nll':float(nll.mean()),'token_nll':nll.tolist(),
+               'limitation':'Real-weight capacity check, not an independent correctness oracle or quality benchmark'})
+
+
+if __name__=='__main__':main()