Signed-off-by: seewoo <seewoo@ucsc.edu> Co-authored-by: Claude <noreply@anthropic.com>
65 lines
2.4 KiB
Python
65 lines
2.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Backbone validation for Jina Embeddings V5 (issue #50337).
|
|
|
|
The V5 family ships two backbones under one `architectures` entry: `-small` is
|
|
a Qwen3 decoder (which vLLM implements), while `-nano` is a bidirectional
|
|
EuroBERT encoder (which it does not). Upstream ships a separate
|
|
`configuration_*.py` per repository, so the only signal distinguishing them is
|
|
`is_decoder`, which the encoder variant sets to False.
|
|
"""
|
|
|
|
from types import SimpleNamespace
|
|
from typing import cast
|
|
|
|
import pytest
|
|
from transformers import PretrainedConfig
|
|
|
|
from vllm.config import ModelConfig
|
|
from vllm.model_executor.models.config import (
|
|
MODELS_CONFIG_MAP,
|
|
JinaEmbeddingsV5ModelConfig,
|
|
)
|
|
|
|
|
|
def _model_config(hf_config: PretrainedConfig) -> ModelConfig:
|
|
"""Minimal stand-in for ModelConfig; only hf_config is read."""
|
|
return cast(ModelConfig, SimpleNamespace(hf_config=hf_config))
|
|
|
|
|
|
@pytest.mark.cpu_test
|
|
def test_registered_for_the_architecture():
|
|
"""The handler only runs if it is wired to the architecture name."""
|
|
assert MODELS_CONFIG_MAP["JinaEmbeddingsV5Model"] is JinaEmbeddingsV5ModelConfig
|
|
|
|
|
|
@pytest.mark.cpu_test
|
|
def test_encoder_backbone_is_rejected():
|
|
"""An encoder checkpoint must fail fast, naming the reason.
|
|
|
|
Without this, loading proceeds until every `q_norm`/`k_norm` weight is
|
|
reported as uninitialized, which does not point at the actual problem.
|
|
"""
|
|
model_config = _model_config(PretrainedConfig(is_decoder=False))
|
|
|
|
with pytest.raises(NotImplementedError, match="is_decoder=False"):
|
|
JinaEmbeddingsV5ModelConfig.verify_and_update_model_config(model_config)
|
|
|
|
|
|
@pytest.mark.cpu_test
|
|
def test_supported_decoder_backbone_is_accepted():
|
|
"""The Qwen3-based variants must keep loading.
|
|
|
|
`-small` omits `is_decoder` entirely, so an absent attribute has to be
|
|
treated as a decoder. The first assertion pins that assumption: if
|
|
PretrainedConfig ever gains an `is_decoder=False` default, this fails here
|
|
rather than silently rejecting a supported checkpoint.
|
|
"""
|
|
absent = PretrainedConfig()
|
|
assert not hasattr(absent, "is_decoder")
|
|
|
|
JinaEmbeddingsV5ModelConfig.verify_and_update_model_config(_model_config(absent))
|
|
JinaEmbeddingsV5ModelConfig.verify_and_update_model_config(
|
|
_model_config(PretrainedConfig(is_decoder=True))
|
|
)
|