modelinfo-cli 1.4.1__tar.gz → 1.4.2__tar.gz

{modelinfo_cli-1.4.1/src/modelinfo_cli.egg-info → modelinfo_cli-1.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: modelinfo-cli
-Version: 1.4.1
+Version: 1.4.2
 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-1.4.1 → modelinfo_cli-1.4.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "modelinfo-cli"
-version = "1.4.1"
+version = "1.4.2"
 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-1.4.1 → modelinfo_cli-1.4.2}/src/modelinfo/__init__.py

@@ -2,4 +2,4 @@
 modelinfo - A high-performance CLI utility for inspecting ML model checkpoints.
 """
 
-__version__ = "1.4.1"
+__version__ = "1.4.2"

{modelinfo_cli-1.4.1 → modelinfo_cli-1.4.2}/src/modelinfo/architecture.py

@@ -1,5 +1,3 @@
-import os
-import json
 from typing import Any, Dict, Tuple
 
 def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None) -> Tuple[int, int, bool]:
@@ -10,16 +8,16 @@ def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None)
     num_layers = 0
     kv_dim = 0
     is_estimate = False
-    
+
     metadata = tensors.get("__metadata__", {})
     gen_arch = metadata.get("general.architecture")
-    
+
     # 1. Attempt explicit GGUF metadata
     if gen_arch:
         arch_str = str(gen_arch)
         num_layers = metadata.get(f"{arch_str}.block_count", 0)
         kv_heads = metadata.get(f"{arch_str}.attention.head_count_kv", 0)
-        
+
         key_length = metadata.get(f"{arch_str}.attention.key_length")
         if not key_length:
             embed_len = metadata.get(f"{arch_str}.embedding_length", 0)
@@ -28,7 +26,7 @@ def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None)
                 key_length = embed_len // q_heads
             else:
                 key_length = 0
-                
+
         if kv_heads > 0 and key_length > 0:
             kv_dim = kv_heads * key_length
             if num_layers > 0:
@@ -40,7 +38,7 @@ def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None)
         num_attention_heads = config.get("num_attention_heads", 1)
         num_key_value_heads = config.get("num_key_value_heads", num_attention_heads)
         hidden_size = config.get("hidden_size", 0)
-        
+
         if num_attention_heads > 0:
             head_dim = hidden_size // num_attention_heads
             kv_dim = num_key_value_heads * head_dim
@@ -51,11 +49,11 @@ def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None)
     layers_set = set()
     found_fused = False
     found_k_proj = False
-    
+
     for name, meta in tensors.items():
         if name == "__metadata__":
             continue
-            
+
         parts = name.split(".")
         if "layers" in parts:
             idx = parts.index("layers")
@@ -71,7 +69,7 @@ def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None)
             shape = meta.get("shape", [])
             if len(shape) >= 2:
                 kv_dim = shape[0]
-                
+
         if "qkv_proj.weight" in name or "c_attn.weight" in name:
             found_fused = True
             if not found_k_proj:
@@ -82,7 +80,7 @@ def extract_architecture(tensors: Dict[str, Any], config: Dict[str, Any] = None)
     num_layers = len(layers_set)
     if found_fused and not found_k_proj and kv_dim > 0:
         is_estimate = True
-        
+
     return num_layers, kv_dim, is_estimate
 
 def identify_architecture_name(tensors: Dict[str, Any], num_layers: int, config: Dict[str, Any] = None) -> str:
@@ -90,18 +88,18 @@ def identify_architecture_name(tensors: Dict[str, Any], num_layers: int, config:
     if config and "architectures" in config and config["architectures"]:
         arch_title = config["architectures"][0]
         return f"{arch_title} ({num_layers} layers)" if num_layers else arch_title
-        
+
     metadata = tensors.get("__metadata__", {})
     gen_arch = metadata.get("general.architecture")
-    
+
     if gen_arch:
         arch_title = str(gen_arch).title()
         return f"{arch_title} ({num_layers} transformer layers)" if num_layers else arch_title
-        
+
     for name in tensors.keys():
         if name == "__metadata__":
             continue
-            
+
         name_lower = name.lower()
         if "llama" in name_lower:
             return f"Llama ({num_layers} transformer layers)" if num_layers else "Llama"
@@ -109,5 +107,5 @@ def identify_architecture_name(tensors: Dict[str, Any], num_layers: int, config:
             return f"Mistral ({num_layers} transformer layers)" if num_layers else "Mistral"
         if "qwen" in name_lower:
             return f"Qwen ({num_layers} transformer layers)" if num_layers else "Qwen"
-        
-    return f"Generic Transformer ({num_layers} layers)" if num_layers > 0 else "Unknown Architecture"
+
+    return f"Generic Transformer ({num_layers} layers)" if num_layers > 0 else "Unknown Architecture"                        

{modelinfo_cli-1.4.1 → modelinfo_cli-1.4.2}/src/modelinfo/cli.py

@@ -207,7 +207,7 @@ def main(argv: Sequence[str] | None = None) -> int:
                 console.print(f"[red]Error analyzing model '{model_path}': {e}[/red]")
                 return 1
             
-        print_compare_info(models, args.max_vram, gpu_name=gpu_name_display)
+        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]
@@ -228,7 +228,7 @@ def main(argv: Sequence[str] | None = None) -> int:
         console.print(f"[red]Error: {e}[/red]")
         return 1
 
-    print_model_info(**info, max_vram_gb=gpu_vram_gb if gpu_vram_gb else 8.0, gpu_name=gpu_name_display)
+    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-1.4.1 → modelinfo_cli-1.4.2}/src/modelinfo/parsers/huggingface.py

@@ -126,7 +126,7 @@ def fetch_huggingface_repo(repo_id: str, fetch_tensors: bool = False) -> Tuple[D
             def fetch_shard(shard: str):
                 return shard, _fetch_safetensors_header(repo_id, shard)
                 
-            with concurrent.futures.ThreadPoolExecutor(max_workers=min(8, len(unique_shards))) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=max(1, min(8, len(unique_shards)))) as executor:
                 future_to_shard = {executor.submit(fetch_shard, shard): shard for shard in unique_shards}
                 for future in concurrent.futures.as_completed(future_to_shard):
                     shard, shard_header = future.result()

{modelinfo_cli-1.4.1 → modelinfo_cli-1.4.2/src/modelinfo_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: modelinfo-cli
-Version: 1.4.1
+Version: 1.4.2
 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