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 13, 17:00 UTC
[CI Failure] `nm-testing/Qwen2-0.5B-Instruct-FP8-SkipQKV` was removed from HF. Skip it in tests (#28170)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Vadim Gimpelson committed
Nov 6, 2025 at 05:22 UTC
f948ab69458552b18925f82a8833c51d6f5b6f67
1 file changed
+6
-1
tests/quantization/test_fp8.py
+6
-1
@@ -18,7 +18,12 @@ from vllm.platforms import current_platform
18
19
MODELS = [
20
"neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV",
21
- "nm-testing/Qwen2-0.5B-Instruct-FP8-SkipQKV",
21
+ # The checkpoint below was removed from the HF.
22
+ # TODO: add a small replacement checkpoint.
23
+ pytest.param(
24
+ "nm-testing/Qwen2-0.5B-Instruct-FP8-SkipQKV",
25
+ marks=pytest.mark.skip(reason="Checkpoint removed from HF."),
26
+ ),
27
]
28
29