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, 01:00 UTC
[CI/Build] Fix test failure due to updated model repo (#21375)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jul 22, 2025 at 23:39 UTC
35366ae57c8d18a33fb5d12baf95c29dd86bd075
1 file changed
+2
-2
tests/models/registry.py
+2
-2
@@ -167,9 +167,9 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
167
"DeepseekV3ForCausalLM": _HfExamplesInfo("deepseek-ai/DeepSeek-V3", # noqa: E501
168
trust_remote_code=True),
169
"Ernie4_5_ForCausalLM": _HfExamplesInfo("baidu/ERNIE-4.5-0.3B-PT",
170
- trust_remote_code=True),
170
+ min_transformers_version="4.54"),
171
"Ernie4_5_MoeForCausalLM": _HfExamplesInfo("baidu/ERNIE-4.5-21B-A3B-PT",
172
- trust_remote_code=True),
172
+ min_transformers_version="4.54"),
173
"ExaoneForCausalLM": _HfExamplesInfo("LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"), # noqa: E501
174
"Exaone4ForCausalLM": _HfExamplesInfo("LGAI-EXAONE/EXAONE-4.0-32B"), # noqa: E501
175
"Fairseq2LlamaForCausalLM": _HfExamplesInfo("mgleize/fairseq2-dummy-Llama-3.2-1B"), # noqa: E501