mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-22 15:32:08 +00:00
11 lines
361 B
Plaintext
11 lines
361 B
Plaintext
|
diff a/server/text_generation_server/layers/gptq/exllamav2.py b/server/text_generation_server/layers/gptq/exllamav2.py (rejected hunks)
|
||
|
@@ -119,6 +119,8 @@ def ext_make_q_matrix(w: dict, temp_dq, key: str = None):
|
||
|
none_tensor,
|
||
|
temp_dq,
|
||
|
)
|
||
|
+ else:
|
||
|
+ RuntimeError("Cannot create handle")
|
||
|
|
||
|
|
||
|
DEVICE = None
|