xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 21:45:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Model] Adding torch compile annotations to chatglm (#15624)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-03-28 21:14:09 +08:00 committed by GitHub
parent 0b4167526d
commit 91276c5721
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/chatglm.py
View File

@ -10,6 +10,7 @@ from torch import nn
from torch.nn import LayerNorm from torch.nn import LayerNorm
from vllm.attention import Attention from vllm.attention import Attention
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, VllmConfig from vllm.config import CacheConfig, VllmConfig
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
from vllm.model_executor.layers.activation import SiluAndMul from vllm.model_executor.layers.activation import SiluAndMul
@ -293,6 +294,7 @@ class GLMTransformer(nn.Module):
return hidden_states return hidden_states
@support_torch_compile
class ChatGLMModel(nn.Module): class ChatGLMModel(nn.Module):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""): def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):