[Bugfix] Fix num_hidden_layers when Qwen2-Audio 7B (#1803)
### What this PR does / why we need it?
Fix num_hidden_layers when Qwen2-Audio 7B and #1760 :
```
INFO 07-15 04:38:53 [platform.py:174] PIECEWISE compilation enabled on NPU. use_inductor not supported - using only ACL Graph mode
Traceback (most recent call last):
File "/workspace/test1.py", line 58, in <module>
main(audio_count)
File "/workspace/test1.py", line 38, in main
llm = LLM(model="Qwen/Qwen2-Audio-7B-Instruct",
File "/vllm-workspace/vllm/vllm/entrypoints/llm.py", line 271, in __init__
self.llm_engine = LLMEngine.from_engine_args(
File "/vllm-workspace/vllm/vllm/engine/llm_engine.py", line 494, in from_engine_args
vllm_config = engine_args.create_engine_config(usage_context)
File "/vllm-workspace/vllm/vllm/engine/arg_utils.py", line 1286, in create_engine_config
config = VllmConfig(
File "/usr/local/python3.10.17/lib/python3.10/site-packages/pydantic/_internal/_dataclasses.py", line 123, in __init__
s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
File "/vllm-workspace/vllm/vllm/config.py", line 4624, in __post_init__
current_platform.check_and_update_config(self)
File "/vllm-workspace/vllm-ascend/vllm_ascend/platform.py", line 180, in check_and_update_config
update_aclgraph_sizes(vllm_config)
File "/vllm-workspace/vllm-ascend/vllm_ascend/utils.py", line 307, in update_aclgraph_sizes
num_hidden_layers = vllm_config.model_config.hf_config.num_hidden_layers
File "/usr/local/python3.10.17/lib/python3.10/site-packages/transformers/configuration_utils.py", line 211, in __getattribute__
return super().__getattribute__(key)
AttributeError: 'Qwen2AudioConfig' object has no attribute 'num_hidden_layers'
```
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Closes: https://github.com/vllm-project/vllm-ascend/issues/1780
https://github.com/vllm-project/vllm-ascend/issues/1760
https://github.com/vllm-project/vllm-ascend/issues/1276
https://github.com/vllm-project/vllm-ascend/issues/359
- vLLM version: v0.10.0
- vLLM main:
7728dd77bb
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
@@ -260,6 +260,61 @@ class TestUtils(TestBase):
|
||||
hits = utils.vllm_version_is.cache_info().hits
|
||||
self.assertEqual(hits, 1)
|
||||
|
||||
def test_get_max_hidden_layers(self):
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
class SimpleConfig(PretrainedConfig):
|
||||
|
||||
def __init__(self, num_hidden_layers=12):
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
|
||||
def to_dict(self):
|
||||
return {"num_hidden_layers": self.num_hidden_layers}
|
||||
|
||||
self.assertEqual(utils.get_max_hidden_layers(SimpleConfig()), 12)
|
||||
self.assertEqual(utils.get_max_hidden_layers(SimpleConfig(24)), 24)
|
||||
|
||||
class NestedConfig(PretrainedConfig):
|
||||
|
||||
def to_dict(self):
|
||||
return {
|
||||
"model": {
|
||||
"encoder": {
|
||||
"num_hidden_layers": 8
|
||||
},
|
||||
"decoder": {
|
||||
"num_hidden_layers": 12
|
||||
}
|
||||
},
|
||||
"other_setting": True
|
||||
}
|
||||
|
||||
self.assertEqual(utils.get_max_hidden_layers(NestedConfig()), 12)
|
||||
|
||||
class MultiValueConfig(PretrainedConfig):
|
||||
|
||||
def to_dict(self):
|
||||
return {
|
||||
"num_hidden_layers": 6,
|
||||
"submodule": {
|
||||
"num_hidden_layers": 18,
|
||||
"subsub": {
|
||||
"num_hidden_layers": 9
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
self.assertEqual(utils.get_max_hidden_layers(MultiValueConfig()), 18)
|
||||
|
||||
class NoLayerConfig(PretrainedConfig):
|
||||
|
||||
def to_dict(self):
|
||||
return {"attention_heads": 8}
|
||||
|
||||
with self.assertRaises(ValueError) as context:
|
||||
utils.get_max_hidden_layers(NoLayerConfig())
|
||||
self.assertIn("num_hidden_layers", str(context.exception))
|
||||
|
||||
def test_update_aclgraph_sizes(self):
|
||||
# max_num_batch_sizes < len(original_sizes)
|
||||
test_compilation_config = CompilationConfig(
|
||||
|
||||
Reference in New Issue
Block a user