Fix an error in dummy weight loading for quantization models (#18855)

Signed-off-by: Chenyaaang <chenyangli@google.com>

Fix an error in dummy weight loading for quantization models (#18855)
Signed-off-by: Chenyaaang <chenyangli@google.com>
f8977c23 · Chenyaaang · GitHub · f274581f · f8977c23
Unverified Commit f8977c23 authored May 29, 2025 by Chenyaaang Committed by GitHub May 29, 2025
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

vllm/model_executor/model_loader/weight_utils.py vllm/model_executor/model_loader/weight_utils.py +1 -1

No files found.
--- a/vllm/model_executor/model_loader/weight_utils.py
+++ b/vllm/model_executor/model_loader/weight_utils.py
@@ -696,7 +696,7 @@ def initialize_dummy_weights(
                # Note: We avoid using torch.rank_like as it doesn't currently
                # support the generator argument.
                param.copy_((high - low) *
-                            torch.rand(*param.shape,
+                            torch.rand(param.shape,
                                       generator=generator,
                                       dtype=param.dtype,
                                       layout=param.layout,