A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[CI/Build] Fix param mismatch in `test_eagle_correctness` (#22847)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Aug 14, 2025 at 01:55 UTC
b4b78d63170ff0b1e5310c295473109d92ee51c2
1 file changed
+5
-1
tests/v1/e2e/test_spec_decode.py
+5
-1
@@ -146,7 +146,11 @@ def test_ngram_correctness(
146
marks=pytest.mark.skip(reason="Skipping due to CI OOM issues")),
147
],
148
ids=[
149
- "qwen3_eagle3", "llama3_eagle", "llama3_eagle3", "llama4_eagle",
149
+ # TODO: Re-enable this once tests/models/test_initialization.py is fixed, see PR #22333 #22611 # noqa: E501
150
+ # "qwen3_eagle3",
151
+ "llama3_eagle",
152
+ "llama3_eagle3",
153
+ "llama4_eagle",
154
"llama4_eagle_mm"
155
])
156
@pytest.mark.parametrize("attn_backend",