[Perf] Optimize batch invariant with fused rms norm, 2.1% E2E latency improvement (#40413)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
@@ -61,10 +61,6 @@ def fused_add_rms_norm(
|
||||
) -> tuple[torch.Tensor, torch.Tensor]:
|
||||
from vllm import _custom_ops as ops
|
||||
|
||||
if envs.VLLM_BATCH_INVARIANT:
|
||||
return rms_norm_batch_invariant(
|
||||
x + residual, weight, variance_epsilon
|
||||
), x + residual
|
||||
ops.fused_add_rms_norm(
|
||||
x,
|
||||
residual,
|
||||
|
||||
Reference in New Issue
Block a user