[Docs] Enable fail_on_warning for the docs build in CI (#25580)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-09-24 19:30:33 +00:00
committed by GitHub
parent f84a472a03
commit 8c853050e7
20 changed files with 81 additions and 87 deletions
@@ -57,7 +57,7 @@ else:
FusedMoEPermuteExpertsUnpermute = None # type: ignore
FusedMoEPrepareAndFinalize = None # type: ignore
def eplb_map_to_physical_and_record(
def _eplb_map_to_physical_and_record(
topk_ids: torch.Tensor, expert_load_view: torch.Tensor,
logical_to_physical_map: torch.Tensor,
logical_replica_count: torch.Tensor,
@@ -65,6 +65,7 @@ else:
# CPU fallback: no EPLB so just return as is
return topk_ids
eplb_map_to_physical_and_record = _eplb_map_to_physical_and_record
if is_rocm_aiter_moe_enabled():
from vllm.model_executor.layers.fused_moe.rocm_aiter_fused_moe import ( # noqa: E501
@@ -807,12 +808,11 @@ def maybe_roundup_hidden_size(
if necessary.
Args:
hidden_size(int): Layer hidden-size
hidden_size: Layer hidden-size
act_dtype: Data type of the layer activations.
quant_config(FusedMoEQuantConfig): Fused MoE quantization configuration.
moe_parallel_config(FusedMoEParallelConfig): Fused MoE parallelization
strategy configuration.
quant_config: Fused MoE quantization configuration.
moe_parallel_config: Fused MoE parallelization strategy configuration.
Return:
Rounded up hidden_size if rounding up is required based on the configs.
Original hidden size otherwise.
@@ -13,7 +13,7 @@ from collections import defaultdict
from collections.abc import Generator
from contextlib import contextmanager
from pathlib import Path
from typing import Any, Callable, Optional, Union
from typing import IO, Any, Callable, Optional, Union
import filelock
import huggingface_hub.constants
@@ -102,7 +102,7 @@ def get_lock(model_name_or_path: Union[str, Path],
@contextmanager
def atomic_writer(filepath: Union[str, Path],
mode: str = 'w',
encoding: Optional[str] = None):
encoding: Optional[str] = None) -> Generator[IO]:
"""
Context manager that provides an atomic file writing routine.
+12 -8
View File
@@ -1445,14 +1445,18 @@ class Qwen3VLForConditionalGeneration(nn.Module, SupportsMultiModal,
**NOTE**: If mrope is enabled (default setting for Qwen3VL
opensource models), the shape will be `(3, seq_len)`,
otherwise it will be `(seq_len,).
pixel_values: Pixel values to be fed to a model.
`None` if no images are passed.
image_grid_thw: Tensor `(n_images, 3)` of image 3D grid in LLM.
`None` if no images are passed.
pixel_values_videos: Pixel values of videos to be fed to a model.
`None` if no videos are passed.
video_grid_thw: Tensor `(n_videos, 3)` of video 3D grid in LLM.
`None` if no videos are passed.
intermediate_tensors: Intermediate tensors from previous pipeline
stages.
inputs_embeds: Pre-computed input embeddings.
**kwargs: Additional keyword arguments including:
- pixel_values: Pixel values to be fed to a model.
`None` if no images are passed.
- image_grid_thw: Tensor `(n_images, 3)` of image 3D grid in
LLM. `None` if no images are passed.
- pixel_values_videos: Pixel values of videos to be fed to a
model. `None` if no videos are passed.
- video_grid_thw: Tensor `(n_videos, 3)` of video 3D grid in
LLM. `None` if no videos are passed.
"""
if intermediate_tensors is not None:
+2 -3
View File
@@ -944,11 +944,10 @@ class Zamba2ForCausalLM(nn.Module, HasInnerState, IsHybrid):
hidden_states: torch.Tensor,
) -> Optional[torch.Tensor]:
"""Compute logits for next token prediction.
Args:
hidden_states: Hidden states from model forward pass
sampling_metadata: Metadata for sampling process
Returns:
Logits for next token prediction
"""