[Distributed] Add opt-in FlashInfer PCIe IPC all-reduce backend (#53576)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Yongye Zhu
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
e16b5e518d
commit
446c769482
@@ -396,6 +396,7 @@ def test_flashinfer_all_reduce_precedes_nccl(monkeypatch: pytest.MonkeyPatch) ->
|
||||
fi_ar_comm.all_reduce.return_value = output
|
||||
communicator = CudaCommunicator.__new__(CudaCommunicator)
|
||||
communicator.fi_ar_comm = fi_ar_comm
|
||||
communicator.fi_pcie_ipc_ar_comm = None
|
||||
communicator.pynccl_comm = Mock(world_size=8)
|
||||
communicator.qr_comm = None
|
||||
nccl_selector = Mock(return_value=True)
|
||||
|
||||
Reference in New Issue
Block a user