huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 03:14:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix the import error

Browse Source 
Signed-off-by: yuanwu <yuan.wu@intel.com>
This commit is contained in:
yuanwu 2025-05-11 23:05:37 +00:00
parent cfcbd80fb4
commit f0acbbf10c
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
backends/gaudi/server/text_generation_server/models/__init__.py
View File

@ -38,6 +38,7 @@ __all__ = [
] ]
from text_generation_server.models.globals import ATTENTION from text_generation_server.models.globals import ATTENTION
VLM_BATCH_TYPES = set()
FLASH_ATT_ERROR_MESSAGE = "{} requires Flash Attention enabled models." FLASH_ATT_ERROR_MESSAGE = "{} requires Flash Attention enabled models."
FLASH_ATTENTION = False FLASH_ATTENTION = False
@ -155,6 +156,9 @@ if FLASH_ATTENTION:
} }
__all__.append(VLM_BATCH_TYPES)
class ModelType(enum.Enum): class ModelType(enum.Enum):
DEEPSEEK_V2 = { DEEPSEEK_V2 = {
"type": "deepseek_v2", "type": "deepseek_v2",