[NVFP4] Support NVFP4 dense models from modelopt and compressed-tensors on AMD Instinct MI300, MI355X and Hopper through emulation (#35733)

Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Kyle Sayers <kylesayrs@gmail.com>

tests/quantization/test_compressed_tensors.py

@@ -366,9 +366,6 @@ def test_compressed_tensors_kv_cache_fp8_per_attn_head(vllm_runner):
         assert output
 
 
-@pytest.mark.skipif(
-    not current_platform.is_cuda(), reason="This test is skipped on non-CUDA platform."
-)
 @pytest.mark.parametrize(
     "args",
     [
@@ -398,7 +395,7 @@ def test_compressed_tensors_nvfp4(vllm_runner, args):
             assert qkv_proj.scheme.group_size == 16
 
         llm.apply_model(check_model)
-        output = llm.generate_greedy("Hello my name is", max_tokens=4)
+        output = llm.generate_greedy(["Hello my name is"], max_tokens=4)
         print(output)
         assert output