modelinfo-cli 1.4.2__tar.gz → 1.4.3__tar.gz

{modelinfo_cli-1.4.2/src/modelinfo_cli.egg-info → modelinfo_cli-1.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: modelinfo-cli
-Version: 1.4.2
+Version: 1.4.3
 Summary: A CLI tool to inspect ML checkpoints (.safetensors, .gguf, .pt) and calculate inference VRAM, multi-GPU memory splits, and vLLM serving capacity.
 Author: ModelInfo Contributors
 License: MIT

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "modelinfo-cli"
-version = "1.4.2"
+version = "1.4.3"
 description = "A CLI tool to inspect ML checkpoints (.safetensors, .gguf, .pt) and calculate inference VRAM, multi-GPU memory splits, and vLLM serving capacity."
 readme = "README.md"
 requires-python = ">=3.10"

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3}/src/modelinfo/__init__.py

@@ -2,4 +2,4 @@
 modelinfo - A high-performance CLI utility for inspecting ML model checkpoints.
 """
 
-__version__ = "1.4.2"
+__version__ = "1.4.3"

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3}/src/modelinfo/cli.py

@@ -3,7 +3,6 @@ import json
 import os
 import sys
 from typing import Sequence
-
 from modelinfo.architecture import identify_architecture_name
 from modelinfo.calculator import calculate_footprint
 from modelinfo.parsers.gguf import parse_gguf_header
@@ -12,6 +11,29 @@ from modelinfo.parsers.safetensors import parse_safetensors_header
 from modelinfo.ui import console, print_model_info, print_compare_info
 
 
+class VersionAction(argparse.Action):
+    def __init__(self, option_strings, dest=argparse.SUPPRESS, default=argparse.SUPPRESS, help="show program's version number and exit"):
+        super().__init__(
+            option_strings=option_strings,
+            dest=dest,
+            default=default,
+            nargs=0,
+            help=help,
+        )
+
+    def __call__(self, parser, namespace, values, option_string=None):
+        from importlib.metadata import PackageNotFoundError, version
+        from modelinfo import __version__
+
+        try:
+            ver = version("modelinfo-cli")
+        except PackageNotFoundError:
+            ver = __version__
+
+        print(f"{parser.prog} {ver}")
+        parser.exit()
+
+
 def parse_args(argv: Sequence[str] | None = None) -> argparse.Namespace:
     parser = argparse.ArgumentParser(
         prog="modelinfo",
@@ -72,6 +94,11 @@ def parse_args(argv: Sequence[str] | None = None) -> argparse.Namespace:
         default=0.9,
         help="vLLM gpu_memory_utilization ratio (default 0.9). Reserves 10 percent for PyTorch context.",
     )
+    parser.add_argument(
+        "-v",
+        "--version",
+        action=VersionAction,
+    )
 
     return parser.parse_args(argv)
 
@@ -114,6 +141,8 @@ def analyze_model(
     elif file_path_lower.endswith(".pt") or file_path_lower.endswith(".bin"):
         tensors = parse_pytorch_header(file_path)
         format_name = "PyTorch"
+    elif os.path.isdir(file_path):
+        raise IsADirectoryError(f"'{file_path}' is a directory. Please provide the path to a specific weights file (e.g. .safetensors, .gguf, .pt) inside the directory.")
     else:
         raise ValueError(f"File '{file_path}' not found locally and does not appear to be a Hugging Face repository ID.")
         
@@ -190,43 +219,35 @@ def main(argv: Sequence[str] | None = None) -> int:
             
         models = []
         for model_path in args.file:
-            try:
-                info = analyze_model(
-                    model_path, 
-                    args.context, 
-                    gpu_count, 
-                    fetch_tensors=args.tensors,
-                    topology=args.topology,
-                    strategy=args.strategy,
-                    is_vllm=args.vllm,
-                    gpu_vram_gb=gpu_vram_gb if gpu_vram_gb else 0.0,
-                    gpu_util=args.gpu_util
-                )
-                models.append((model_path.split("/")[-1], info))
-            except Exception as e:
-                console.print(f"[red]Error analyzing model '{model_path}': {e}[/red]")
-                return 1
+            info = analyze_model(
+                model_path, 
+                args.context, 
+                gpu_count, 
+                fetch_tensors=args.tensors,
+                topology=args.topology,
+                strategy=args.strategy,
+                is_vllm=args.vllm,
+                gpu_vram_gb=gpu_vram_gb if gpu_vram_gb else 0.0,
+                gpu_util=args.gpu_util
+            )
+            models.append((model_path.split("/")[-1], info))
             
         print_compare_info(models, gpu_vram_gb if gpu_vram_gb else args.max_vram, gpu_name=gpu_name_display)
         return 0
         
     file_path = args.file[0]
     
-    try:
-        info = analyze_model(
-            file_path, 
-            args.context, 
-            gpu_count, 
-            fetch_tensors=args.tensors,
-            topology=args.topology,
-            strategy=args.strategy,
-            is_vllm=args.vllm,
-            gpu_vram_gb=gpu_vram_gb if gpu_vram_gb else 0.0,
-            gpu_util=args.gpu_util
-        )
-    except Exception as e:
-        console.print(f"[red]Error: {e}[/red]")
-        return 1
+    info = analyze_model(
+        file_path, 
+        args.context, 
+        gpu_count, 
+        fetch_tensors=args.tensors,
+        topology=args.topology,
+        strategy=args.strategy,
+        is_vllm=args.vllm,
+        gpu_vram_gb=gpu_vram_gb if gpu_vram_gb else 0.0,
+        gpu_util=args.gpu_util
+    )
 
     print_model_info(**info, max_vram_gb=gpu_vram_gb if gpu_vram_gb else args.max_vram, gpu_name=gpu_name_display)
     return 0

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3}/src/modelinfo/hardware.py

@@ -21,6 +21,7 @@ KNOWN_GPUS = {
     "rtx4060ti16gb": 16.0,
     "rtx4060ti": 8.0,
     "rtx4060": 8.0,
+    "rtx4050" : 6.0,
     "rtx3090ti": 24.0,
     "rtx3090": 24.0,
     "rtx3080ti": 12.0,
@@ -31,6 +32,7 @@ KNOWN_GPUS = {
     "rtx3060ti": 8.0,
     "rtx306012gb": 12.0,
     "rtx3060": 8.0,
+    "rtx3050ti" : 4.0,
     "rtx3050": 8.0,
     "rtx2080ti": 11.0,
     "rtx2080super": 8.0,
@@ -40,6 +42,11 @@ KNOWN_GPUS = {
     "rtx2060super": 8.0,
     "rtx206012gb": 12.0,
     "rtx2060": 6.0,
+    "gtx1660super": 6.0,
+    "gtx1660ti" : 6.0,
+    "gtx1660": 6.0,
+    "gtx1650super": 4.0,
+    "gtx1650": 4.0,
     "gtx1080ti": 11.0,
     "gtx1080": 8.0,
     "gtx1070ti": 8.0,
@@ -106,6 +113,9 @@ KNOWN_GPUS = {
     "rx6650xt": 8.0,
     "rx6600xt": 8.0,
     "rx6600": 8.0,
+    "rx580": 8.0,
+    "rx570": 4.0,
+
 
     # --- AMD Data Center / Pro ---
     "mi300x": 192.0,

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3}/src/modelinfo/parsers/huggingface.py

@@ -29,7 +29,7 @@ def _get_hf_token() -> str | None:
             
     return None
 
-def _make_request(url: str, headers: Dict[str, str] = None) -> bytes:
+def _make_request(url: str, headers: Dict[str, str] = None, limit: int | None = None) -> bytes:
     if headers is None:
         headers = {}
         
@@ -40,12 +40,14 @@ def _make_request(url: str, headers: Dict[str, str] = None) -> bytes:
     req = urllib.request.Request(url, headers=headers)
     try:
         with urllib.request.urlopen(req, timeout=10) as response:
+            if limit is not None:
+                return response.read(limit)
             return response.read()
     except urllib.error.HTTPError as e:
         if e.code == 401:
-            raise PermissionError(f"Gated Model or Invalid Token: Please set HF_TOKEN environment variable to access {url}")
+            raise PermissionError(f"Gated/Private Model or Invalid Token (401 Unauthorized). Set the HF_TOKEN environment variable to access {url}")
         if e.code == 404:
-            raise FileNotFoundError(f"File not found on Hugging Face Hub: {url}")
+           raise FileNotFoundError(f"Could not find repository or file on Hugging Face (404 Not Found): {url}")
         raise
 
 def _fetch_safetensors_header(repo_id: str, filename: str) -> Dict[str, Any]:
@@ -54,10 +56,10 @@ def _fetch_safetensors_header(repo_id: str, filename: str) -> Dict[str, Any]:
     # 1. Fetch the first 500KB in a single roundtrip
     headers = {"Range": "bytes=0-500000"}
     try:
-        chunk = _make_request(url, headers=headers)
+        chunk = _make_request(url, headers=headers, limit=500000)
     except urllib.error.HTTPError as e:
         if e.code == 416: # Range Not Satisfiable (file is smaller than 500KB)
-            chunk = _make_request(url)
+            chunk = _make_request(url, limit=500000)
         else:
             raise
             
@@ -72,7 +74,7 @@ def _fetch_safetensors_header(repo_id: str, filename: str) -> Dict[str, Any]:
     else:
         # 3. Double-roundtrip only if the header is massive (>500KB)
         headers = {"Range": f"bytes=8-{8+header_size-1}"}
-        json_bytes = _make_request(url, headers=headers)
+        json_bytes = _make_request(url, headers=headers, limit=header_size)
         
     return json.loads(json_bytes)
 
@@ -86,7 +88,9 @@ def fetch_huggingface_repo(repo_id: str, fetch_tensors: bool = False) -> Tuple[D
         api_data = json.loads(_make_request(api_url).decode("utf-8"))
     except urllib.error.HTTPError as e:
         if e.code == 401:
-            raise PermissionError(f"Gated Model: Please set HF_TOKEN environment variable to access {repo_id}")
+            raise PermissionError(f"Gated/Private Model (401 Unauthorized). Set the HF_TOKEN environment variable to access {repo_id}")
+        if e.code == 404:
+             raise FileNotFoundError(f"Could not find repository on Hugging Face (404 Not Found): {repo_id}")
         raise
         
     siblings = api_data.get("siblings", [])

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3/src/modelinfo_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: modelinfo-cli
-Version: 1.4.2
+Version: 1.4.3
 Summary: A CLI tool to inspect ML checkpoints (.safetensors, .gguf, .pt) and calculate inference VRAM, multi-GPU memory splits, and vLLM serving capacity.
 Author: ModelInfo Contributors
 License: MIT

{modelinfo_cli-1.4.2 → modelinfo_cli-1.4.3}/src/modelinfo_cli.egg-info/SOURCES.txt

@@ -21,5 +21,6 @@ src/modelinfo_cli.egg-info/entry_points.txt
 src/modelinfo_cli.egg-info/requires.txt
 src/modelinfo_cli.egg-info/top_level.txt
 tests/test_calculator.py
+tests/test_cli.py
 tests/test_constraints.py
 tests/test_parsers.py

modelinfo_cli-1.4.3/tests/test_cli.py

@@ -0,0 +1,12 @@
+import pytest
+
+from modelinfo import __version__
+from modelinfo.cli import parse_args
+
+
+def test_version_flag_prints_installed_version(capsys):
+    with pytest.raises(SystemExit) as exc_info:
+        parse_args(["--version"])
+
+    assert exc_info.value.code == 0
+    assert f"modelinfo {__version__}" in capsys.readouterr().out