[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>
(cherry picked from commit 6cf7b26bd4)

requirements/cuda.txt

@@ -9,7 +9,7 @@ torchaudio==2.11.0
 # These must be updated alongside torch
 torchvision==0.26.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
 torchcodec >= 0.14
-PyNvVideoCodec==2.1.0
+PyNvVideoCodec==2.0.4
 # FlashInfer should be updated together with the Dockerfile
 flashinfer-python==0.6.13
 flashinfer-cubin==0.6.13

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

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.