quantprobe 1.5.2__tar.gz → 1.6.0__tar.gz

{quantprobe-1.5.2/quantprobe.egg-info → quantprobe-1.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantprobe
-Version: 1.5.2
+Version: 1.6.0
 Summary: Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes.
 Author: Federico Sciuca
 License: MIT

{quantprobe-1.5.2 → quantprobe-1.6.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "quantprobe"
-version = "1.5.2"
+version = "1.6.0"
 description = "Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes."
 readme = "README.md"
 license = { text = "MIT" }

{quantprobe-1.5.2 → quantprobe-1.6.0}/quantprobe/__init__.py

@@ -8,4 +8,4 @@ Three commands, all grounded in measured laws (see LAWS.md in the repo):
 Every constant in `plan` is fitted from measurements published in the repo, including two
 pre-registered hardware predictions confirmed within 8%.
 """
-__version__ = "1.5.2"
+__version__ = "1.6.0"

{quantprobe-1.5.2 → quantprobe-1.6.0}/quantprobe/auto.py

@@ -68,7 +68,36 @@ def pick_source(files, t):
     return hi[0] if hi else max(cands)
 
 
+def _wizard(a):
+    """No model given: detect, ask two questions, go. The full pipeline with zero flags."""
+    print("quantprobe auto - interactive (no flags needed; `quantprobe auto --help` for the full list)")
+    try:
+        from . import detect as detmod
+        d, _ = detmod.detect()
+        print(f"\n  this machine [auto-detected]: {d['vram']:g} GB VRAM @ {d['vram_bw']:g} GB/s | "
+              f"{d['ram']:g} GB RAM @ {d['ram_bw']:g} GB/s | disk {d['disk_bw']:g} GB/s")
+    except Exception:
+        pass
+    try:
+        m = input(f"\n  model - preset ({', '.join(MODEL_REPOS)}) or HF GGUF repo id [qwen3-30b]: ").strip() or "qwen3-30b"
+        print("\n  [1] best standard quant for this machine, ready to run  (skips quantization)")
+        print("  [2] full custom: probe YOUR model's fragile layers (~30-60 min), build its personalized GGUF")
+        print("  [3] hit a speed target (asks for tok/s)")
+        c = input("  choice [1]: ").strip() or "1"
+        if c == "2":
+            a.custom = True
+        elif c == "3":
+            a.tps = float(input("  target tok/s: ").strip())
+        r = input("  launch chat when ready? [Y/n]: ").strip().lower()
+        a.run = r != "n"
+    except EOFError:
+        raise SystemExit("no model given and no terminal to ask. Pass one: quantprobe auto qwen3-30b [--custom] [--run]")
+    a.target = m
+
+
 def run(a):
+    if a.target is None:
+        _wizard(a)
     target = a.target
     if target in MODEL_REPOS:
         repo, t, ac, ne, moe = MODEL_REPOS[target]
@@ -111,6 +140,12 @@ def run(a):
     scored.sort()
     _, _, path, size, bits, best = scored[0]
 
+    if getattr(a, "custom", False) and want_bits >= 3.5 and not getattr(a, "force_custom", False):
+        print(f"\n[quantprobe auto --custom] this machine doesn't need the surgery: the optimizer")
+        print(f"  wants ~{want_bits:g}-bit here, and at >=3.5 bits standard community quants match the")
+        print(f"  depth-aware recipe on quality - the fragile-band fix only pays below ~3 bits (Laws 1-2).")
+        print(f"  Fetching the optimal standard quant instead. Build anyway: --force-custom.")
+        a.custom = False
     if getattr(a, "custom", False):
         src = pick_source(files, t)
         if not src:

{quantprobe-1.5.2 → quantprobe-1.6.0}/quantprobe/cli.py

@@ -92,14 +92,16 @@ def main():
     hwargs(o)
 
     au = sub.add_parser("auto", help="ONE command: model in, running setup out - optimizer picks the bits, the closest quant is fetched, run command printed")
-    au.add_argument("target", help="model preset (qwen3-30b, qwen3-coder, glm-air, laguna-s, gemma-12b, mistral-7b) or a HF GGUF repo id")
+    au.add_argument("target", nargs="?", default=None,
+                    help="model preset (qwen3-30b, qwen3-coder, glm-air, laguna-s, gemma-12b, mistral-7b) or a HF GGUF repo id; omit it and quantprobe ASKS (interactive)")
     au.add_argument("--dir", default="./models", help="download directory (default ./models)")
     au.add_argument("--run", action="store_true", help="launch chat immediately after the download")
     hwargs(au)
     au.add_argument("--tps", type=float, default=None, help="target tok/s for the optimizer")
     au.add_argument("--max-quality", type=float, default=None)
     au.add_argument("--allow-prune", action="store_true"); au.add_argument("--any-runtime", action="store_true")
-    au.add_argument("--custom", action="store_true", help="THE PRODUCT: fetch a high-precision source, probe YOUR model (~30-60 min), build a depth-aware GGUF personalized to it")
+    au.add_argument("--custom", action="store_true", help="THE PRODUCT: fetch a high-precision source, probe YOUR model (~30-60 min), build a depth-aware GGUF personalized to it (machine-gated: skipped with an explanation when this box doesn't need sub-3-bit surgery)")
+    au.add_argument("--force-custom", action="store_true", help="build the depth-aware GGUF even when the optimizer says this machine doesn't need it")
     au.add_argument("--serve", action="store_true", help="with --run: llama-server instead of chat")
     au.add_argument("--extra", default=None)
 

{quantprobe-1.5.2 → quantprobe-1.6.0/quantprobe.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantprobe
-Version: 1.5.2
+Version: 1.6.0
 Summary: Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes.
 Author: Federico Sciuca
 License: MIT