Switch to llama-cpp-python

pyproject.toml

@@ -16,7 +16,14 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Software Development :: Libraries :: Python Modules",
 ]
-dependencies = ["gguf>=0", "pydantic>=2", "safetensors>=0", "torch>=2"]
+dependencies = [
+    "gguf>=0",
+    "llama-cpp-python>=0",
+    "psutil>=7",
+    "pydantic>=2",
+    "safetensors>=0",
+    "torch>=2",
+]
 
 [project.urls]
 Homepage = "https://git.tomfos.tr/tom/llm-gguf-tools"
@@ -24,7 +31,7 @@ Homepage = "https://git.tomfos.tr/tom/llm-gguf-tools"
 "Source" = "https://git.tomfos.tr/tom/llm-gguf-tools"
 
 [dependency-groups]
-dev = ["pytest>=8", "ruff>=0", "uv>=0"]
+dev = ["mypy>=1", "pytest>=8", "ruff>=0", "types-psutil>=7", "uv>=0"]
 
 [tool.uv]
 package = true
@@ -72,6 +79,7 @@ ignore = [
     "PLR0913", # too many arguments
     "PLR0915", # too many statements
     "PLR0917", # too many positional arguments
+    "PLR2004", # magic numbers
     "PLR6301", # method could be static
     "RUF029",  # async methods that don't await
     "S104",    # binding to all interfaces
@@ -94,3 +102,6 @@ required-imports = ["from __future__ import annotations"]
 
 [tool.ruff.lint.pydocstyle]
 convention = "google"
+
+[tool.mypy]
+exclude = ["work/"]