Skip to content

Commit bb4018d

Browse files
Add get_device_total_memory warning
Signed-off-by: Paweł Olejniczak <[email protected]>
1 parent 4cf9660 commit bb4018d

File tree

1 file changed

+2
-0
lines changed

1 file changed

+2
-0
lines changed

vllm_gaudi/platform.py

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -93,6 +93,8 @@ def get_device_total_memory(cls, device_id: int = 0) -> int:
9393
# default_max_num_batched_tokens, in order to avoid the
9494
# error in hpu_perf_test, while also preventing a
9595
# NotImplementedError in test_defaults_with_usage_context.
96+
logger.warning("This is a workaround! Please check the NOTE "
97+
"in the get_device_total_memory definition.")
9698

9799
total_hpu_memory = 0
98100

0 commit comments

Comments
 (0)