Enhance Ollama model management and performance tuning

- Updated the `provision_llm` function to utilize the `/api/tags` endpoint for verifying available models, improving accuracy in model management.
- Introduced a new `already_have_ollama_tag` function to ensure exact tag matching, preventing mismatches during model checks.
- Enhanced the `pull_stream` function to require a successful status from the API before proceeding, ensuring reliable model downloads.
- Added logic to handle unwritten blob files, improving the robustness of the model pulling process.
- Updated documentation and tests to reflect these changes, ensuring clarity and reliability in Ollama model operations.

tests/test_llm_runtime.py

@@ -3,6 +3,7 @@ from pathlib import Path
 import pytest
 
 from gpu_rent.llm_runtime import (
+    already_have_ollama_tag,
     decide_runtime,
     normalize_runtime,
     parse_ollama_models,
@@ -59,3 +60,11 @@ def test_write_preset(tmp_path: Path):
     assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-vl-abliterated:32b"
     write_ollama_models_preset(path, "text")
     assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-abliterate:7b"
+
+
+def test_already_have_ollama_tag_exact_only():
+    have = {"qwen2.5:7b", "foo:latest"}
+    assert already_have_ollama_tag(have, "qwen2.5:7b")
+    assert not already_have_ollama_tag(have, "qwen2.5:3b")
+    assert already_have_ollama_tag(have, "foo")
+    assert already_have_ollama_tag(have, "foo:latest")