diff --git a/vllm/model_executor/layers/fused_moe/layer.py b/vllm/model_executor/layers/fused_moe/layer.py index 5c8f7010f6..9622f9ed88 100644 --- a/vllm/model_executor/layers/fused_moe/layer.py +++ b/vllm/model_executor/layers/fused_moe/layer.py @@ -186,9 +186,10 @@ def FusedMoE( has_bias: Whether expert layers have bias terms is_sequence_parallel: Whether sequence parallelism is enabled reduce_results: Whether to all-reduce the final output. Setting this - to False (to fuse the all-reduce downstream) is only honored on the - late-AR path. - expert_mapping: Expert parameter mapping for weight loading + to False (to fuse the all-reduce downstream) is only honored on + the late-AR path. + ckpt_names: Checkpoint parameter name tuple (gate_proj, down_proj, + up_proj) used for weight loading n_shared_experts: Number of shared experts to fuse into the routed grouped GEMM (ROCm; requires aiter FSE or the router-append path) router_logits_dtype: Data type for router logits buffers diff --git a/vllm/v1/kv_offload/tiering/p2p/manager.py b/vllm/v1/kv_offload/tiering/p2p/manager.py index 3456f95b7e..6949686f44 100644 --- a/vllm/v1/kv_offload/tiering/p2p/manager.py +++ b/vllm/v1/kv_offload/tiering/p2p/manager.py @@ -11,7 +11,7 @@ from __future__ import annotations import time from collections.abc import Iterable, Sequence from dataclasses import dataclass, field -from typing import TYPE_CHECKING +from typing import TYPE_CHECKING, Any from typing_extensions import override @@ -115,7 +115,7 @@ class P2PSecondaryTierManager(SecondaryTierManager): port: int = 7777, backends: list[str] | None = None, num_threads: int = 4, - **kwargs, + **kwargs: Any, ) -> None: """Initialize the P2P secondary tier manager.