Files
vllm-omni/probe/issue-2/probe.py
T
admin 67eb7fdb48
Build Wheel / build (3.11) (pull_request) Failing after 33s
Build Wheel / build (3.12) (pull_request) Failing after 40s
pre-commit / pre-commit (pull_request) Failing after 41s
probe: Qwen-Image conditioning-KV spill probe on RTX 3090 / RTX 5080 (issue 2)
Evidence-only change: probe kit (serve wrapper, API client, PSNR
comparator, offline fp8_v driver), per-host run summaries, and the
findings report. No code changes to the stack.

Verdicts: not-built on both cards. On the 3090 the served reference
ceiling is two condition images with the conditioning cache on
(2.2x the Diffusers nocache baseline, pair PSNR mean 27.57 dB);
four references OOM on the resident BF16 working set, not the KV
(~0.3 GiB/reference, per-request). On the 5080 the server cannot
initialize under any flag: init_parameters materializes the
unquantized skeleton on-device before quantization/offload engage.
Also documents that the recipe's deploy-YAML extras route for
prefix_kv_cache_dtype does not reach the served transformer on
8484d85d (offline Omni engine kwarg does).
2026-10-08 00:58:29 -04:00

164 lines
5.4 KiB
Python

#!/usr/bin/env python
"""Issue 2 probe client: reference-conditioned requests through the API.
Functional pass: one-, two-, and four-reference fixtures at seed 2301.
Measured pass: the four-reference fixture at seeds 2301-2304.
Every request mirrors the sealed Diffusers baseline attempt
2026-10-07T170729Z-q3-4r (same frozen references, same rendered prompt,
20 steps, true_cfg_scale 1.0, fixture resolution, no negative prompt),
submitted one at a time through POST /v1/images/edits.
Usage: probe.py --out RUN_DIR [--functional] [--measured] [--host H:P]
"""
from __future__ import annotations
import argparse
import base64
import hashlib
import json
import pathlib
import time
import requests
W = pathlib.Path.home() / "Projects/vllm-omni-val/issue2"
SUITE = (
pathlib.Path.home()
/ ".local/share/multi-model-helper-server/data/evaluation/media/image/references-suite-2"
)
STEPS = 20
CFG = 1.0
FUNCTIONAL_FIXTURES = (
"edit-expression-ysolde", # 1 reference
"edit-compose-pair", # 2 references
"edit-compose-four", # 4 references
)
MEASURED_FIXTURE = "edit-compose-four"
MEASURED_SEEDS = (2301, 2302, 2303, 2304)
def submit(host: str, fixture: dict, seed: int) -> tuple[dict, bytes | None]:
files = []
handles = []
for ref in fixture["references"]:
path = SUITE / f"{ref}.png"
handle = open(path, "rb")
handles.append(handle)
files.append(("image[]", (path.name, handle, "image/png")))
data = {
"model": "Qwen/Qwen-Image-2.1",
"prompt": fixture["prompt"],
"seed": str(seed),
"num_inference_steps": str(STEPS),
"true_cfg_scale": str(CFG),
"size": f"{fixture['width']}x{fixture['height']}",
"n": "1",
"response_format": "b64_json",
"output_format": "png",
"return_stage_metrics": "true",
}
rec: dict = {
"fixture_id": None,
"seed": seed,
"n_references": len(fixture["references"]),
"steps": STEPS,
"true_cfg_scale": CFG,
"size": f"{fixture['width']}x{fixture['height']}",
}
t0 = time.time()
try:
response = requests.post(
f"http://{host}/v1/images/edits", data=data, files=files, timeout=1200
)
rec["wall_s"] = round(time.time() - t0, 2)
rec["http"] = response.status_code
if response.status_code == 200:
body = response.json()
png = base64.b64decode(body["data"][0]["b64_json"])
rec["bytes"] = len(png)
rec["sha256"] = hashlib.sha256(png).hexdigest()
rec["usage"] = body.get("usage")
for key in ("stage_metrics", "metrics", "timings"):
if body.get(key):
rec[key] = body[key]
return rec, png
rec["error"] = response.text[:2000]
return rec, None
except Exception as exc: # noqa: BLE001 - recorded as the probe result
rec["wall_s"] = round(time.time() - t0, 2)
rec["error"] = f"{type(exc).__name__}: {exc}"
return rec, None
finally:
for handle in handles:
handle.close()
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--out", required=True, type=pathlib.Path)
parser.add_argument("--host", default="127.0.0.1:8091")
parser.add_argument("--functional", action="store_true")
parser.add_argument("--measured", action="store_true")
parser.add_argument(
"--fixture",
default=MEASURED_FIXTURE,
help="fixture id for --measured (default: edit-compose-four)",
)
parser.add_argument(
"--seeds",
type=lambda s: tuple(int(x) for x in s.split(",")),
default=MEASURED_SEEDS,
help="comma-separated seeds for --measured",
)
args = parser.parse_args()
fixtures = json.loads((W / "fixtures.json").read_text())
args.out.mkdir(parents=True, exist_ok=True)
plan: list[tuple[str, pathlib.Path, int]] = []
if args.functional:
for fixture_id in FUNCTIONAL_FIXTURES:
plan.append(
(fixture_id, args.out / "functional" / f"{fixture_id}.png", 2301)
)
if args.measured:
for seed in args.seeds:
plan.append(
(
args.fixture,
args.out / "measured" / f"{args.fixture}.s{seed}.png",
seed,
)
)
records = []
for fixture_id, out_path, seed in plan:
rec, png = submit(args.host, fixtures[fixture_id], seed)
rec["fixture_id"] = fixture_id
records.append(rec)
print(json.dumps(rec), flush=True)
if png is not None:
out_path.parent.mkdir(parents=True, exist_ok=True)
out_path.write_bytes(png)
elif rec.get("http") == 200:
print(f"warning: 200 but no image for {fixture_id} seed {seed}", flush=True)
suffix_parts = []
if args.functional:
suffix_parts.append("functional")
if args.measured:
suffix_parts.append(f"measured-{args.fixture}")
suffix = "-".join(suffix_parts)
(args.out / f"{suffix}.json").write_text(
json.dumps(records, indent=1) + "\n"
)
ok = all(r.get("http") == 200 and "sha256" in r for r in records)
print(("PASS" if ok else "FAIL") + f" {len(records)} requests", flush=True)
return 0 if ok else 1
if __name__ == "__main__":
raise SystemExit(main())