[Docs] Fix warnings in mkdocs build (continued) (#25042)

Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
This commit is contained in:
Wenlong Wang
2025-09-20 11:45:18 +00:00
committed by GitHub
parent e08a3a3fdb
commit 032d661d27
7 changed files with 24 additions and 15 deletions
+2 -2
View File
@@ -1229,8 +1229,8 @@ def get_kv_cache_configs(vllm_config: VllmConfig,
Args:
vllm_config: The global VllmConfig
kv_cache_specs: List of dict[layer_name, KVCacheSpec] for each worker.
available_memory: Memory available for KV cache in bytes for each
worker.
available_memory: Memory available for KV cache in bytes for each
worker.
Returns:
The generated KVCacheConfigs for each worker.
+5 -5
View File
@@ -351,17 +351,17 @@ def generate_uniform_probs(
without a seed.
Args:
num_tokens : int
num_tokens: int
Total number of tokens.
num_draft_tokens : List[List[int]]
num_draft_tokens: List[List[int]]
Number of draft tokens per request.
generators : Optional[Dict[int, torch.Generator]]
generators: Optional[Dict[int, torch.Generator]]
A dictionary mapping indices in the batch to
`torch.Generator` objects.
device : torch.device
device: torch.device
The device on which to allocate the tensor.
Returns:
uniform_rand : torch.Tensor
uniform_rand: torch.Tensor
A tensor of shape `(num_tokens, )` containing uniform
random values in the range [0, 1).
"""
+1 -1
View File
@@ -1479,7 +1479,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
Args:
scheduler_output: The scheduler output containing scheduled encoder
inputs.
inputs.
Returns:
A tuple of (mm_kwargs, req_ids_pos) where:
+2 -1
View File
@@ -205,7 +205,8 @@ def gather_mm_placeholders(
"""
Reconstructs the embeddings from the placeholder tokens.
This is the operation of [scatter_mm_placeholders][].
This is the operation of [`scatter_mm_placeholders`]
[vllm.v1.worker.utils.scatter_mm_placeholders].
"""
if is_embed is None:
return placeholders