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
fix m2 test (#27536)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Oct 27, 2025 at 01:04 UTC
361a7463d33a8866bababc2926e48b60dbb1aadd
1 file changed
+3
-1
tests/models/registry.py
+3
-1
@@ -342,7 +342,9 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
342
"MiniMaxAI/MiniMax-M1-40k", trust_remote_code=True
343
),
344
"MiniMaxM2ForCausalLM": _HfExamplesInfo(
345
- "MiniMaxAI/MiniMax-M2", trust_remote_code=True
345
+ "MiniMaxAI/MiniMax-M2",
346
+ trust_remote_code=True,
347
+ is_available_online=False,
348
),
349
"MistralForCausalLM": _HfExamplesInfo("mistralai/Mistral-7B-Instruct-v0.1"),
350
"MixtralForCausalLM": _HfExamplesInfo(