[Quantization] Deprecate Long Tail of Schemes (#31688)

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

tests/quantization/test_rtn.py

@@ -30,6 +30,10 @@ def test_model_rtn_startup(
     max_tokens: int,
 ) -> None:
     with vllm_runner(
-        model, enforce_eager=True, dtype=dtype, quantization="rtn"
+        model,
+        enforce_eager=True,
+        dtype=dtype,
+        quantization="rtn",
+        allow_deprecated_quantization=True,
     ) as vllm_model:
         vllm_model.generate_greedy(example_prompts, max_tokens)