[torch.compile] Adding torch compile annotations to some models (#9641)

Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
Yongzao
2024-10-24 09:31:42 -07:00
committed by GitHub
co-authored by youkaichao
parent de662d32b5
commit d27cfbf791
7 changed files with 21 additions and 11 deletions
+2
View File
@@ -29,6 +29,7 @@ from torch import nn
from transformers import PretrainedConfig
from vllm.attention import Attention, AttentionMetadata
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, LoRAConfig
from vllm.distributed import (get_pp_group, get_tensor_model_parallel_rank,
get_tensor_model_parallel_world_size)
@@ -263,6 +264,7 @@ class SolarDecoderLayer(nn.Module):
return hidden_states, residual
@support_torch_compile
class SolarModel(nn.Module):
def __init__(