biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Docs] Fix warnings in mkdocs build (continued) (#23743)

Browse Source 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Signed-off-by: Hyogeun Oh (오효근) <ohg3417@gmail.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-08-28 02:17:29 +09:00
committed by GitHub
parent dd58932280
commit 4e4d017b6f
26 changed files with 56 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/v1/core/encoder_cache_manager.py
View File

@@ -255,9 +255,9 @@ def compute_encoder_budget(
Returns:
- Compute budget for encoder execution, measured in number of tokens
from the input sequence.
from the input sequence.
- Space budget for encoder cache size, measured in number of tokens
from the input sequence.
from the input sequence.
"""
if mm_registry.supports_multimodal_inputs(model_config):
max_tokens_by_modality = mm_registry \
@@ -303,9 +303,9 @@ def compute_mm_encoder_budget(
Returns:
- Compute budget for encoder execution, measured in number of tokens
from the input sequence.
from the input sequence.
- Space budget for encoder cache size, measured in number of tokens
from the input sequence.
from the input sequence.
"""
if not max_tokens_by_modality: