From 13680e5542848a6d33b436e4821e868476d060cd Mon Sep 17 00:00:00 2001
From: Alison Shao <54658187+alisonshao@users.noreply.github.com>
Date: Tue, 9 Dec 2025 05:21:35 -0800
Subject: [PATCH] [Test] Skip STANDALONE speculative decoding tests for
 different hidden sizes (#14733)

---
 test/srt/models/test_nvidia_nemotron_nano_v2.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/test/srt/models/test_nvidia_nemotron_nano_v2.py b/test/srt/models/test_nvidia_nemotron_nano_v2.py
index e29be59d3..ab8c2abdc 100644
--- a/test/srt/models/test_nvidia_nemotron_nano_v2.py
+++ b/test/srt/models/test_nvidia_nemotron_nano_v2.py
@@ -24,6 +24,10 @@ class TestNvidiaNemotronNanoV2NVFP4(GSM8KMixin, CustomTestCase):
     other_args = ["--max-mamba-cache-size", "256"]
 
 
+@unittest.skip(
+    "STANDALONE speculative decoding does not yet support target and draft models "
+    "with different hidden sizes (Nemotron-9B: 4480, Llama-3.2-1B: 2048)"
+)
 class TestNvidiaNemotronNanoV2SpeculativeDecoding(GSM8KMixin, CustomTestCase):
     accuracy = 0.87
     model = "nvidia/NVIDIA-Nemotron-Nano-9B-v2"
@@ -49,6 +53,10 @@ class TestNvidiaNemotronNanoV2SpeculativeDecoding(GSM8KMixin, CustomTestCase):
     ]
 
 
+@unittest.skip(
+    "STANDALONE speculative decoding does not yet support target and draft models "
+    "with different hidden sizes (Nemotron-9B: 4480, Llama-3.2-1B: 2048)"
+)
 class TestNvidiaNemotronNanoV2SpeculativeDecodingBF16Cache(GSM8KMixin, CustomTestCase):
     accuracy = 0.87
     model = "nvidia/NVIDIA-Nemotron-Nano-9B-v2"