mxfp8 online quant move to new frontend (#40152)
Signed-off-by: Vasiliy Kuznetsov <vasiliy@meta.com>
This commit is contained in:
@@ -515,14 +515,6 @@ class Fp8OnlineLinearMethod(Fp8LinearMethod):
|
||||
|
||||
initialize_online_processing(layer)
|
||||
|
||||
# TODO: remove this check once the following RFC is resolved.
|
||||
# https://github.com/vllm-project/vllm/issues/33314
|
||||
# Subclasses (e.g. Mxfp8OnlineLinearMethod) only need the weight
|
||||
# registration above and manage their own kernel, so skip fp8_linear
|
||||
# kernel creation for them.
|
||||
if type(self) is not Fp8OnlineLinearMethod:
|
||||
return
|
||||
|
||||
self.fp8_linear = init_fp8_linear_kernel(
|
||||
activation_quant_key=self.activation_quant_key,
|
||||
weight_quant_key=self.weight_quant_key,
|
||||
|
||||
Reference in New Issue
Block a user