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

Stop using title frontmatter and fix doc that can only be reached by search (#20623)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-07-08 11:27:40 +01:00
committed by GitHub
parent b4bab81660
commit b942c094e3
81 changed files with 82 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/design/mm_processing.md
View File

@@ -1,6 +1,4 @@
---
title: Multi-Modal Data Processing
---
# Multi-Modal Data Processing
To enable various optimizations in vLLM such as [chunked prefill][chunked-prefill] and [prefix caching](../features/automatic_prefix_caching.md), we use [BaseMultiModalProcessor][vllm.multimodal.processing.BaseMultiModalProcessor] to provide the correspondence between placeholder feature tokens (e.g. `<image>`) and multi-modal inputs (e.g. the raw input image) based on the outputs of HF processor.