A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 11:00 UTC
[Bugfix] Fix QKVCrossParallelLinear::sync_weight_attrs for PyTorch compile (#17844)
Signed-off-by: Andrzej Kotłowski <akotlowski@habana.ai>
Andrzej Kotłowski committed
May 14, 2025 at 11:39 UTC
38fe728d60f7aeed721a7d1ba1644a26e0a487c6
1 file changed
+2
-2
vllm/model_executor/layers/linear.py
+2
-2
@@ -1425,8 +1425,8 @@ class QKVCrossParallelLinear(LinearBase):
1425
):
1426
missing_attrs_dict = {
1427
k: getattr(src_param, k)
1428
- for k in (set(src_param.__dict__.keys()) -
1429
- set(tgt_param.__dict__.keys()))
1428
+ for k in (set(vars(src_param).keys()) -
1429
+ set(vars(tgt_param).keys()))
1430
}
1431
# TODO(Isotr0py): handle bitsandbytes 8bit
1432
use_bitsandbytes_4bit = getattr(src_param, "use_bitsandbytes_4bit",