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"})

scripts/deep-probe.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+"""deep-probe.py — one chat completion at ~43.6k prompt tokens, temp 0, 512
+generated, streamed; decode = completion_tokens / (total - ttft)."""
+import json, time, urllib.request
+
+TARGET_BYTES = int(43600 * 3.8)
+
+def build():
+    parts, n = [], 0
+    with open("/home/dank/corpora/out/calib.jsonl") as f:
+        for line in f:
+            p = json.loads(line)["prompt"]
+            parts.append(p)
+            n += len(p.encode())
+            if n >= TARGET_BYTES:
+                break
+    return "".join(parts)
+
+def main(salt):
+    body = json.dumps({
+        "model": "frank-primary",
+        "messages": [{"role": "user", "content": f"[probe {salt}] Continue and summarize this material in English, 400 words.\n\n" + build()}],
+        "temperature": 0.0, "max_tokens": 512,
+        "stream": True, "stream_options": {"include_usage": True},
+    }).encode()
+    req = urllib.request.Request("http://localhost:7770/v1/chat/completions",
+        data=body, headers={"Content-Type": "application/json"})
+    t0 = time.time(); ttft = None; ctok = 0; usage = {}
+    with urllib.request.urlopen(req, timeout=2400) as r:
+        for raw in r:
+            line = raw.decode().strip()
+            if not line.startswith("data:"):
+                continue
+            d = line[5:].strip()
+            if d == "[DONE]":
+                break
+            j = json.loads(d)
+            if j.get("usage"):
+                usage = j["usage"]
+            for ch in j.get("choices", []):
+                delta = (ch.get("delta") or {})
+                piece = delta.get("content") or delta.get("reasoning_content") or ""
+                if piece and ttft is None:
+                    ttft = time.time() - t0
+                ctok += 1
+    total = time.time() - t0
+    gen = usage.get("completion_tokens") or ctok
+    dec = gen / (total - (ttft or 0)) if total > (ttft or 0) else 0
+    print(json.dumps({"salt": salt, "prompt_tokens": usage.get("prompt_tokens"),
+                      "completion_tokens": gen, "ttft_s": round(ttft or 0, 2),
+                      "total_s": round(total, 1), "decode_tps": round(dec, 2)}))
+
+if __name__ == "__main__":
+    import sys
+    main(sys.argv[1] if len(sys.argv) > 1 else "x")

scripts/frank-primary.env

@@ -73,7 +73,7 @@ FRANK_PRIMARY_IMAGE=stilldeadcode/radiance@sha256:4c3f484564bb2872784e46b0a59cbd
 # .rad files; the raw HF download and its staging dir live beside it and
 # are never mounted.
 FRANK_PRIMARY_MODEL_DIR=/home/dank/models/rad
-FRANK_PRIMARY_MODEL_FILE=qwen4exp-fp8-native.rad
+FRANK_PRIMARY_MODEL_FILE=qwen4exp-swift15-w4dn8-i8-hc8m.rad
 FRANK_PRIMARY_STATE_DIR=/home/dank/radiance-state
 # The state dir's tune/ subdirectory holds rad-tune's kernel-selection
 # cache (the engine's selector reads $RADIANCE_HOME/tune/<machine>.tune
@@ -161,4 +161,4 @@ FRANK_PRIMARY_EXTRA_ARGS=
 # container measured 177,109 MiB (1,857,127,997,440 B = 173.0 GiB; the
 # plan-only estimate 172.76 GiB covers the data planes but not the metadata
 # tail) - floor sits just under the payload.
-FRANK_PRIMARY_RAD_MIN_MIB=177000
+FRANK_PRIMARY_RAD_MIN_MIB=110000