[Model] Add support for MPT (#334)
This commit is contained in:
@@ -12,7 +12,7 @@ from vllm import cache_ops
|
||||
from vllm import pos_encoding_ops
|
||||
from vllm.model_executor.input_metadata import InputMetadata
|
||||
|
||||
_SUPPORTED_HEAD_SIZES = [64, 80, 96, 128]
|
||||
_SUPPORTED_HEAD_SIZES = [64, 80, 96, 112, 128]
|
||||
|
||||
|
||||
class PagedAttention(nn.Module):
|
||||
|
||||
Reference in New Issue
Block a user