We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent b00f02a commit f4be123Copy full SHA for f4be123
vllm_gaudi/ops/hpu_fp8.py
@@ -71,8 +71,6 @@ def __init__(self, quant_config: Fp8Config, layer: torch.nn.Module):
71
# disable DeepGemm support.
72
self.allow_deep_gemm = False
73
74
- self.topk_indices_dtype = None
75
-
76
def create_weights(self, *args, **kwargs) -> None:
77
if hpu_ops.is_hpu_gaudi2:
78
kwargs['weight_loader'] = hpu_ops.gaudi_weight_wrapper(kwargs.get('weight_loader'))
0 commit comments