[docs] Fix the docs build (#48008)

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Martin Hickey
2026-07-08 15:47:22 -07:00
committed by GitHub
co-authored by Harry Mellor
parent 5f85975624
commit 6cf7b26bd4
2 changed files with 6 additions and 5 deletions
@@ -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
+2 -2
View File
@@ -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.