huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Dummy workaround for CPU.

Browse Source
This commit is contained in:
Nicolas Patry 2023-09-06 14:35:02 +02:00
parent 1987d37603
commit 14bbd311c1
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/text_generation_server/utils/layers.py
View File

@ -18,7 +18,10 @@ from accelerate import init_empty_weights
from text_generation_server.utils.gptq.quant_linear import QuantLinear from text_generation_server.utils.gptq.quant_linear import QuantLinear
major, _minor = torch.cuda.get_device_capability() try:
major, _minor = torch.cuda.get_device_capability()
except Exception:
major = 1
HAS_EXLLAMA = False HAS_EXLLAMA = False
CAN_EXLLAMA = major >= 8 CAN_EXLLAMA = major >= 8
if os.getenv("DISABLE_EXLLAMA") == "True": if os.getenv("DISABLE_EXLLAMA") == "True":