20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix tensor parallel for qwen2 classification model (#10297)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py 2024-11-14 10:54:59 +08:00 committed by GitHub
parent ac49b59d8b
commit 15bb8330aa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/models/embedding/language/test_cls_models.py
View File

@ -21,14 +21,14 @@ def test_classification_models(
model: str,
dtype: str,
) -> None:
with vllm_runner(model, dtype=dtype) as vllm_model:
vllm_outputs = vllm_model.classify(example_prompts)
with hf_runner(model,
dtype=dtype,
auto_cls=AutoModelForSequenceClassification) as hf_model:
hf_outputs = hf_model.classify(example_prompts)
with vllm_runner(model, dtype=dtype) as vllm_model:
vllm_outputs = vllm_model.classify(example_prompts)
print(hf_outputs, vllm_outputs)
# check logits difference

7
vllm/model_executor/models/qwen2_cls.py
View File

@ -69,9 +69,14 @@ class Qwen2ForSequenceClassification(nn.Module):
self.model = Qwen2Model(vllm_config=vllm_config,
prefix=maybe_prefix(prefix, "model"))
# hidden_states from Qwen2Model has been reduced,
# the input of score layer is not parallelized.
self.score = RowParallelLinear(config.hidden_size,
config.num_labels,
quant_config=quant_config)
quant_config=quant_config,
input_is_parallel=False,
bias=False,
prefix=maybe_prefix(prefix, "score"))
self._pooler = Pooler.from_config_with_defaults(
pooler_config,
pooling_type=PoolingType.LAST,