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] Skip gpt_big model test because of broken HF model (#22848)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Aug 14, 2025 at 04:36 UTC
df0e0f023e1be63d259280ccb9caf5547302ad30
1 file changed
+2
-1
tests/models/registry.py
+2
-1
@@ -195,7 +195,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
195
"GPT2LMHeadModel": _HfExamplesInfo("openai-community/gpt2",
196
{"alias": "gpt2"}),
197
"GPTBigCodeForCausalLM": _HfExamplesInfo("bigcode/starcoder",
198
- {"tiny": "bigcode/tiny_starcoder_py"}), # noqa: E501
198
+ extras={"tiny": "bigcode/tiny_starcoder_py"}, # noqa: E501
199
+ min_transformers_version="4.55.1"),
200
"GPTJForCausalLM": _HfExamplesInfo("Milos/slovak-gpt-j-405M",
201
{"6b": "EleutherAI/gpt-j-6b"}),
202
"GPTNeoXForCausalLM": _HfExamplesInfo("EleutherAI/pythia-70m",