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

[Misc] Avoid misleading warning messages (#10438)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2024-11-19 16:54:58 +08:00 committed by GitHub
parent 272e31c0bd
commit 382b6a4852
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/models/chatglm.py
View File

@ -575,8 +575,7 @@ class ChatGLMModel(nn.Module):
return hidden_states
class ChatGLMBaseModel(nn.Module, SupportsLoRA, SupportsPP,
SupportsMultiModal):
class ChatGLMBaseModel(nn.Module, SupportsLoRA, SupportsPP):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
super().__init__()
@ -695,7 +694,7 @@ class ChatGLM(ChatGLMBaseModel):
embedding_padding_modules = []
class ChatGLMV(ChatGLMBaseModel):
class ChatGLMV(ChatGLMBaseModel, SupportsMultiModal):
packed_modules_mapping = {
"query_key_value": ["query_key_value"],
"dense_h_to_4h": ["dense_h_to_4h"],

10
vllm/model_executor/models/qwen.py
View File

@ -870,7 +870,7 @@ def dummy_data_for_qwen(
return DummyData(seq_data, mm_data)
class QWenBaseModel(nn.Module, SupportsMultiModal, SupportsPP, SupportsLoRA):
class QWenBaseModel(nn.Module, SupportsPP, SupportsLoRA):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
super().__init__()
@ -1024,7 +1024,7 @@ class QWenLLM(QWenBaseModel):
embedding_padding_modules = []
class QWenVL(QWenBaseModel):
class QWenVL(QWenBaseModel, SupportsMultiModal):
packed_modules_mapping = {
"c_attn": ["c_attn"],
"gate_up_proj": [
@ -1062,7 +1062,7 @@ class QWenVL(QWenBaseModel):
@MULTIMODAL_REGISTRY.register_max_image_tokens(MAX_QWEN_IMG_TOKENS)
@INPUT_REGISTRY.register_dummy_data(dummy_data_for_qwen)
@INPUT_REGISTRY.register_input_processor(input_processor_for_qwen)
class QWenLMHeadModel(QWenBaseModel, SupportsLoRA):
class QWenLMHeadModel(QWenBaseModel, SupportsMultiModal, SupportsLoRA):
"""
QWenLMHeadModel is not only applicable to LLM but also to VL, which is not
conducive to the current integration logic of LoRA in vLLM. Therefore, it
@ -1083,7 +1083,7 @@ class QWenLMHeadModel(QWenBaseModel, SupportsLoRA):
config = vllm_config.model_config.hf_config
# Initialize VL
if hasattr(config, "visual"):
return QWenVL(vllm_config=vllm_config)
return QWenVL(vllm_config=vllm_config, prefix=prefix)
# Initialize LLM
else:
return QWenLLM(vllm_config=vllm_config)
return QWenLLM(vllm_config=vllm_config, prefix=prefix)