swift15: env -> candidate payload, RAD floor 110000 (measured 116,416 MiB)

scripts/bench-probe.py

@@ -7,7 +7,7 @@ import json, sys, urllib.request
 
 TARGET = 43600  # tokens
 BYTES_PER_TOK = 3.8
-URL = "http://localhost:7770/completion"
+URL = "http://localhost:7770/v1/completions"
 
 def build_prompt():
     want = int(TARGET * BYTES_PER_TOK)
@@ -26,8 +26,8 @@ def build_prompt():
 def probe(salt):
     prompt = f"[probe {salt}]\n" + build_prompt()
     body = json.dumps({
+        "model": "frank-primary",
         "prompt": prompt, "temperature": 0.0, "max_tokens": 512,
-        "stream": False,
     }).encode()
     req = urllib.request.Request(URL, data=body,
         headers={"Content-Type": "application/json"})