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 16, 22:00 UTC
[Doc] Remove comments incorrectly copied from another project (#6286)
daquexian committed
Jul 11, 2024 at 01:05 UTC
99ded1e1c4dc00baa77beae74602ebafe4921176
1 file changed
-1
vllm/model_executor/layers/linear.py
-1
@@ -743,7 +743,6 @@ class RowParallelLinear(LinearBase):
743
param_data.copy_(loaded_weight)
744
745
def forward(self, input_):
746
- # Set up backprop all-reduce.
746
if self.input_is_parallel:
747
input_parallel = input_
748
else: