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, 14:30 UTC
Restore PlaMo2 unit test as `pfnet/plamo-2-1b` now supports `transformers >=4.56` (#28019)
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Shinichi Hemmi committed
Nov 10, 2025 at 15:50 UTC
a98cc35c34945630883f65f5af5c321c65d03d8b
1 file changed
-2
tests/models/registry.py
-2
@@ -394,8 +394,6 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
394
),
395
"Plamo2ForCausalLM": _HfExamplesInfo(
396
"pfnet/plamo-2-1b",
397
- max_transformers_version="4.55.4",
398
- transformers_version_reason="HF model uses remote code that is not compatible with latest Transformers", # noqa: E501
397
trust_remote_code=True,
398
),
399
"QWenLMHeadModel": _HfExamplesInfo(