Support official semantic llama.cpp releases and document prefill comparison

test_runtime.py

@@ -16,6 +16,8 @@ class RuntimeTests(unittest.TestCase):
    r=Runtime(d)
    with patch.object(r,'prerequisites',return_value={'cuda_ready':False}),patch('runtime.subprocess.Popen') as spawn:
     with self.assertRaises(ValueError):r.start('b9000')
+    with self.assertRaises(ValueError):r.start('v0.5.0')
+    self.assertEqual(r.prerequisites.call_count,2)
     spawn.assert_not_called()
  def test_selection_rollback_persistence(self):
   with tempfile.TemporaryDirectory() as d:
@@ -42,8 +44,8 @@ class RuntimeTests(unittest.TestCase):
     with self.assertRaises(ValueError):r.fit('medium',160000,2)
  def test_official_prereleases_are_not_hidden(self):
   row=dict(tag_name='b11229',name='build',published_at='date',body='notes',html_url='https://github.com/ggml-org/llama.cpp/releases',prerelease=True,draft=False)
-  with tempfile.TemporaryDirectory() as d,patch('runtime.github',return_value=[row]):
-   self.assertTrue(Runtime(d).releases()['releases'][0]['prerelease'])
+  with tempfile.TemporaryDirectory() as d,patch('runtime.github',side_effect=[[row],dict(row,tag_name='v0.5.0',prerelease=False)]):
+   releases=Runtime(d).releases()['releases'];self.assertEqual(releases[0]['tag'],'v0.5.0');self.assertTrue(releases[1]['prerelease'])
  def test_fit_excludes_busy_gpu_and_preserves_context(self):
   with tempfile.TemporaryDirectory() as d:
    r=Runtime(d);r.state.update(active='build',builds=[dict(id='build',backend='CUDA',fit_tool=True)])