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 15, 16:00 UTC
[CI] Disable flaky structure decoding test temporarily. (#15892)
Signed-off-by: Roger Wang <ywang@roblox.com>
Roger Wang committed
Apr 1, 2025 at 10:42 UTC
7e3f7a4ee799b42aea206f6c09b993ea184bfca3
1 file changed
+2
-1
tests/v1/entrypoints/llm/test_struct_output_generate.py
+2
-1
@@ -23,7 +23,8 @@ PARAMS_MODELS_BACKENDS_TOKENIZER_MODE = [
23
("mistralai/Ministral-8B-Instruct-2410", "xgrammar:disable-any-whitespace",
24
"mistral"),
25
("Qwen/Qwen2.5-1.5B-Instruct", "xgrammar:disable-any-whitespace", "auto"),
26
- ("Qwen/Qwen2.5-1.5B-Instruct", "guidance:disable-any-whitespace", "auto"),
26
+ #FIXME: This test is flaky on CI thus disabled
27
+ #("Qwen/Qwen2.5-1.5B-Instruct", "guidance:disable-any-whitespace", "auto"),
28
]
29
30
PARAMS_MODELS_TOKENIZER_MODE = [