Enable flashinfer::trtllm_allreduce_fusion with PDL (#23765)
Co-authored-by: b8zhong <b8zhong@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
b8zhong
gemini-code-assist[bot]
parent
d9dddd4d7d
commit
5fa3bb2eaf
@@ -676,6 +676,7 @@ def flashinfer_allreduce_residual_rmsnorm(
|
||||
workspace=workspace_manager.workspace,
|
||||
pattern=_flashinfer_comm.AllReduceFusionPattern.kARResidualRMSNorm,
|
||||
launch_with_pdl=True,
|
||||
trigger_completion_at_end=trigger_completion_at_end,
|
||||
residual_out=residual_out,
|
||||
norm_out=norm_out,
|
||||
residual_in=residual,
|
||||
|
||||
Reference in New Issue
Block a user