dots/fl/.config/llamacpp/bench.py

#!/usr/bin/env python3
"""
llama.cpp router benchmark → writes a results ledger for later tuning.

SAFETY-FIRST: this GPU also drives the display — VRAM overcommit spills to GTT and can
freeze the whole PC. The script therefore:
  - records the BASELINE VRAM before touching anything (leftover model / browser skews everything)
  - ensures a CLEAN card before EVERY load (incl. the first): resident models are force-unloaded
    via the router API (POST /models/unload), then VRAM is verified with rocm-smi — the poll
    covers driver reclaim lag, older builds without the endpoint (sleep-idle fallback), and
    desktop apps the router doesn't own. Aborts if the card never drains.
  - checks free VRAM right after a model mounts; too tight (--min-free-gb) or GTT ballooning
    (--max-gtt-gb, measured against a PER-MODEL baseline — GTT reclaims slowly) → records a
    ⚠ row and skips generating; the sweep continues after the drain-wait
  - refuses to sweep multiple models blind (no rocm-smi) unless --no-vram-ok

Per model it records decode/prefill t/s, TTFT, VRAM used/free, and the preset's knobs
(ctx, n-cpu-moe, spec-type) parsed from config.ini.

Output: bench-results.md (latest run, overwritten) + bench-history.md (every run, appended)
— both next to this script. Run ON the GPU box. Stdlib only.

  ./bench.py                            # all models the server lists
  ./bench.py -m id1,id2                 # only these
  ./bench.py -x Qwen3-Coder-Next-UD-IQ3_XXS      # skip some (e.g. not downloaded yet)
  ./bench.py -n 512 --ctx 16000         # longer gen + a long-context decode column
Compare a change: edit config.ini → reload server → re-run → diff runs in bench-history.md.
"""
import argparse, json, os, re, subprocess, sys, time, urllib.request, urllib.error
from datetime import datetime

HERE = os.path.dirname(os.path.abspath(__file__))
_smi_warned = False


def rocm_mem(kind="vram"):
    """(used_bytes, total_bytes) from rocm-smi for 'vram' or 'gtt'; (None, None) if unavailable."""
    global _smi_warned
    try:
        out = subprocess.run(["rocm-smi", "--showmeminfo", kind],
                             capture_output=True, text=True, timeout=15).stdout
    except Exception:
        out = ""
    def grab(pat):
        m = re.search(pat + r"\s*:?\s*(\d+)", out)
        return int(m.group(1)) if m else None
    label = "VRAM" if kind == "vram" else "GTT"
    used = grab(label + r" Total Used Memory \(B\)") or grab(r"Used Memory \(B\)")
    total = grab(label + r" Total Memory \(B\)")
    if kind == "vram" and total is None and not _smi_warned:
        _smi_warned = True
        print("  (rocm-smi not readable here — VRAM columns and freeze guards are OFF)", file=sys.stderr)
    return used, total


def with_retries(fn, retries, wait, label=""):
    """Retry on 5xx/connection errors (model still mounting). A deterministic 'failed to
    load' from the router is NOT retried — that's a broken preset, not a slow mount."""
    last = None
    for i in range(retries + 1):
        try:
            return fn()
        except urllib.error.HTTPError as e:
            if e.code < 500:              # 4xx = real client error
                raise
            body = ""
            try:
                body = e.read().decode("utf-8", "ignore")
            except Exception:
                pass
            if "failed to load" in body:  # deterministic → don't burn retries
                raise RuntimeError("model failed to load — check `journalctl -u llama.service`") from None
            last = e
        except (urllib.error.URLError, ConnectionError, TimeoutError) as e:
            last = e
        if i < retries:
            print(f"    … {label} not ready ({last}); waiting {wait}s (try {i + 1}/{retries})", file=sys.stderr)
            time.sleep(wait)
    raise last


def _open(url, key, payload=None, timeout=600):
    data = json.dumps(payload).encode() if payload is not None else None
    hdrs = {"Authorization": f"Bearer {key}"}
    if data:
        hdrs["Content-Type"] = "application/json"
    return urllib.request.urlopen(urllib.request.Request(url, data=data, headers=hdrs), timeout=timeout)


def list_models(base, key):
    d = json.load(_open(base.rstrip("/") + "/models", key))
    return [m["id"] for m in d.get("data", [])]


def force_unload(base, key):
    """Ask the router to unload every resident model (POST /models/unload on the ROOT api,
    not /v1). Harmless no-op on builds without the endpoint — callers fall back to polling."""
    root = re.sub(r"/v1/?$", "", base.rstrip("/"))
    try:
        d = json.load(_open(root + "/models", key, timeout=30))
    except Exception as e:
        print(f"    (router /models not readable: {e} — relying on sleep-idle drain)", file=sys.stderr)
        return
    for m in d.get("data", []):
        if m.get("status", "loaded") != "loaded":   # builds without 'status': try them all
            continue
        try:
            _open(root + "/models/unload", key, {"model": m["id"]}, timeout=30).read()
        except Exception:
            pass                                    # not loaded / endpoint missing — poll covers it


def parse_config(path):
    """{preset: {ctx, ncpumoe, spec}} from the router config.ini."""
    sections, sec = {}, None
    try:
        lines = open(path, encoding="utf-8").read().splitlines()
    except OSError:
        return {}
    for ln in lines:
        s = ln.strip()
        if s.startswith("[") and s.endswith("]"):
            sec = s[1:-1]; sections[sec] = {}
        elif sec and "=" in s and not s.startswith("#"):
            k, v = s.split("=", 1)
            sections[sec][k.strip()] = v.split("#", 1)[0].strip()
    return {sec: {"ctx": kv.get("ctx-size", "-"),
                  "ncpumoe": kv.get("n-cpu-moe", "-"),
                  "spec": kv.get("spec-type", "-") or "-"}
            for sec, kv in sections.items()}


def run(base, key, model, prompt, n, temp, timeout):
    payload = {"model": model, "messages": [{"role": "user", "content": prompt}],
               "max_tokens": n, "temperature": temp, "stream": True,
               "stream_options": {"include_usage": True},
               # llama.cpp extension: makes the server embed its own timings in the stream →
               # the table shows the SAME predicted_per_second as the llama.cpp web UI
               # (without it we fall back to wall-clock estimates, which read lower).
               "timings_per_token": True}
    t0 = time.perf_counter(); ttft = None; ntok = 0; usage = None; timings = None
    for raw in _open(base.rstrip("/") + "/chat/completions", key, payload, timeout):
        line = raw.decode("utf-8", "ignore").strip()
        if not line.startswith("data:"):
            continue
        body = line[5:].strip()
        if body == "[DONE]":
            break
        try:
            c = json.loads(body)
        except ValueError:
            continue
        ch = c.get("choices") or [{}]
        if ch and ch[0].get("delta", {}).get("content"):
            if ttft is None:
                ttft = time.perf_counter() - t0
            ntok += 1
        if c.get("usage"):
            usage = c["usage"]
        if c.get("timings"):
            timings = c["timings"]
    total = time.perf_counter() - t0
    comp = (usage or {}).get("completion_tokens") or ntok
    ptok = (usage or {}).get("prompt_tokens")
    gen_s = total - (ttft or total)
    tg = comp / gen_s if gen_s > 0 else 0.0
    pp = (ptok / ttft) if (ptok and ttft) else None
    if timings:  # llama.cpp's own numbers are authoritative when the router forwards them
        tg = timings.get("predicted_per_second", tg)
        pp = timings.get("prompt_per_second", pp)
        ptok = timings.get("prompt_n", ptok)
    return {"tg": tg, "pp": pp, "ttft": ttft or 0.0, "ptok": ptok or 0}


def wait_drain(drain_gb, window_s, label="", base=None, key=None):
    """Force-unload resident models via the router API, then poll until VRAM used drops
    below drain_gb (card is clean) or the window expires."""
    used, _ = rocm_mem()
    if base and used is not None and used > drain_gb * 1e9:
        force_unload(base, key)
    end = time.time() + window_s
    announced = False
    while used is not None and used > drain_gb * 1e9 and time.time() < end:
        if not announced:
            print(f"    … waiting for VRAM to drain before {label} ({gb(used)} used)", file=sys.stderr)
            announced = True
        time.sleep(5)
        used, _ = rocm_mem()
    return used


def gb(b):
    return f"{b / 1e9:.1f} GB" if b else "-"


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("-u", "--url", default="http://192.168.0.204:11343/v1")
    ap.add_argument("-k", "--key", default="no-key-required")
    ap.add_argument("-m", "--models", default="all", help="comma-separated ids, or 'all'")
    ap.add_argument("-x", "--skip", default="", help="comma-separated ids to skip")
    ap.add_argument("-n", "--tokens", type=int, default=256)
    ap.add_argument("-t", "--temp", type=float, default=0.3)
    ap.add_argument("--ctx", type=int, default=0, help="also record decode at ~this many prompt tokens")
    ap.add_argument("--timeout", type=int, default=600, help="per-request stall timeout (s)")
    ap.add_argument("--config", default=os.path.join(HERE, "config.ini"))
    ap.add_argument("--out", default=os.path.join(HERE, "bench-results.md"))
    ap.add_argument("--history", default=os.path.join(HERE, "bench-history.md"))
    ap.add_argument("--retries", type=int, default=4, help="retries while a model is still mounting")
    ap.add_argument("--retry-wait", type=int, default=15, help="seconds between retries")
    ap.add_argument("--drain-gb", type=float, default=4.0,
                    help="VRAM considered 'clean' below this (raise it if your desktop alone uses more)")
    ap.add_argument("--min-free-gb", type=float, default=1.5,
                    help="SAFETY: stop the sweep if a loaded model leaves less VRAM free than this")
    ap.add_argument("--max-gtt-gb", type=float, default=2.0,
                    help="SAFETY: flag a model if GTT grows more than this over baseline (= VRAM spilling to RAM)")
    ap.add_argument("--unload-wait", type=int, default=360,
                    help="after a too-tight model, wait up to this long for it to unload before continuing "
                         "(sleep-idle-seconds keeps models resident up to 300s)")
    ap.add_argument("--no-vram-ok", action="store_true",
                    help="allow a multi-model sweep even though rocm-smi (and thus the freeze guards) is unavailable")
    a = ap.parse_args()

    models = list_models(a.url, a.key) if a.models == "all" else [m.strip() for m in a.models.split(",")]
    skip = {s.strip() for s in a.skip.split(",") if s.strip()}
    models = [m for m in models if m not in skip]
    cfg = parse_config(a.config)

    used0, total_vram = rocm_mem("vram")
    if total_vram is None and len(models) > 1 and not a.no_vram_ok:
        sys.exit("ABORT: rocm-smi is not readable here, so the VRAM/GTT freeze guards can't work.\n"
                 "Run this ON the GPU box, bench a single model with -m <id>, or pass --no-vram-ok to accept the risk.")
    if used0 is not None and used0 > a.drain_gb * 1e9:
        print(f"⚠ baseline VRAM used is already {gb(used0)} — a leftover model (sleep-idle keeps them "
              f"up to 5 min) or desktop apps (browser!). Results/safety margins will be skewed; "
              f"ideally close GPU apps or wait, then re-run.", file=sys.stderr)

    task = "Write a Python function that merges two sorted lists, with a short docstring and one example."
    filler = ("The quick brown fox jumps over the lazy dog. " * max(1, a.ctx // 9)) if a.ctx else None

    cols = ["model", "cfg ctx", "n-cpu-moe", "spec", "decode t/s", "prefill t/s", "TTFT s", "VRAM used", "VRAM free"]
    if a.ctx:
        cols.append(f"decode@{a.ctx // 1000}k")

    latest = open(a.out, "w", encoding="utf-8")
    hist = open(a.history, "a", encoding="utf-8")
    meta = (f"_Run {datetime.now():%Y-%m-%d %H:%M} · server `{a.url}` · VRAM total {gb(total_vram)} · "
            f"baseline used {gb(used0)} · gen {a.tokens} tok · guards: free≥{a.min_free_gb} GB, GTT+≤{a.max_gtt_gb} GB_")

    def emit(line, both=True):
        print(line)
        latest.write(line + "\n"); latest.flush()
        if both:
            hist.write(line + "\n"); hist.flush()

    latest.write("# llama.cpp benchmark results (latest run)\n\n")
    hist.write(f"\n## run {datetime.now():%Y-%m-%d %H:%M}\n\n")
    emit(meta + "\n")
    emit("| " + " | ".join(cols) + " |")
    emit("|" + "|".join(["---"] * len(cols)) + "|")

    for m in models:
        c = cfg.get(m, {})
        base_cells = [m, c.get("ctx", "-"), c.get("ncpumoe", "-"), c.get("spec", "-")]
        # A CLEAN card before EVERY load (incl. the first): force-unload via the router API,
        # then verify with rocm-smi — double residency = bogus numbers or a freeze.
        u = wait_drain(a.drain_gb, a.unload_wait, m, a.url, a.key)
        if u is not None and u > a.drain_gb * 1e9:
            emit("")
            emit(f"_⚠ aborted before {m}: VRAM still {gb(u)} used after {a.unload_wait}s — something "
                 f"won't unload (leftover model / GPU apps). If that's your normal desktop, raise --drain-gb._")
            print(f"\n⚠ aborted: card not clean ({gb(u)} used).", file=sys.stderr)
            break
        gtt_pre, _ = rocm_mem("gtt")   # per-model GTT baseline — GTT reclaims slowly across swaps
        try:
            # warmup — retries wait out the mount; 'failed to load' aborts immediately
            with_retries(lambda: run(a.url, a.key, m, "hi", 8, a.temp, a.timeout), a.retries, a.retry_wait, m)
            used, _ = rocm_mem("vram")
            gtt, _ = rocm_mem("gtt")
            free = (total_vram - used) if (total_vram and used) else None
            gtt_delta = (gtt - gtt_pre) if (gtt is not None and gtt_pre is not None) else None
            reason = None
            if free is not None and free < a.min_free_gb * 1e9:
                reason = f"only {gb(free)} VRAM free"
            elif gtt_delta is not None and gtt_delta > a.max_gtt_gb * 1e9:
                reason = f"GTT grew {gb(gtt_delta)} = spilling to system RAM"
            if reason:
                # Too tight — do NOT generate (allocates more). Record the row; the sweep continues
                # once this model has fully unloaded (see below).
                hint = ("raise n-cpu-moe" if c.get("ncpumoe", "-") != "-"
                        else "lower ctx / smaller quant / add n-cpu-moe if MoE")
                cells = base_cells + [f"⚠ {reason} — SKIPPED ({hint})", "", "", gb(used), gb(free)]
                if a.ctx:
                    cells.append("")
            else:
                r = with_retries(lambda: run(a.url, a.key, m, task, a.tokens, a.temp, a.timeout),
                                 a.retries, a.retry_wait, m)
                cells = base_cells + [f"{r['tg']:.1f}", (f"{r['pp']:.0f}" if r['pp'] else "-"),
                                      f"{r['ttft']:.2f}", gb(used), gb(free)]
                if a.ctx:
                    rc = with_retries(lambda: run(a.url, a.key, m, filler + "\n\n" + task, a.tokens, a.temp, a.timeout),
                                      a.retries, a.retry_wait, m)
                    cells.append(f"{rc['tg']:.1f}")
        except Exception as e:
            err = f"HTTP {e.code} (check server log)" if isinstance(e, urllib.error.HTTPError) else f"ERROR {e}"
            cells = base_cells + [err] + [""] * (len(cols) - len(base_cells) - 1)
        emit("| " + " | ".join(str(x) for x in cells) + " |")
        # (no post-row wait needed: the pre-load drain above protects the next iteration,
        #  including after ⚠-tight rows where generation was skipped)

    latest.write("\n_Tuning hints: **VRAM free** = headroom to raise `ctx-size` or lower `n-cpu-moe` "
                 "(more experts on GPU → faster). Low decode t/s on an offloaded MoE → lower `n-cpu-moe` "
                 "if free allows. High **baseline used** invalidates the run. For spec/MTP models, check "
                 "the server log's acceptance rate._\n")
    latest.close(); hist.close()
    print(f"\nwrote {a.out} (+ appended {a.history})")


if __name__ == "__main__":
    main()