anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Update docs/architecture/detailed arch design.md

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Hongsheng Liuandgemini-code-assist[bot] authored and GitHub committed 2025-09-26 15:51:49 +08:00
1 parent afe5c2692c
commit e58e62fcbe
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
docs/architecture/detailed arch design.md
+1 -1
View File
@@ -16,7 +16,7 @@ vLLM-omni is a multi-modality extension for vLLM that supports non-autoregressiv
API Server --> OmniLLM/AsyncOmniLLM (New, including multi engines) --> LLMEngine/AsyncLLM --> Engine Core
--> Scheduler (New one for DiT) --> Executor (New one for diffusers) --> Worker (New one for DiT)
--> ModelRunner (New one for AR hiddenstate, New one for DiT) --> RequestState --> OutputProcessoer (New one for final multimodal output)
--> ModelRunner (New one for AR hiddenstate, New one for DiT) --> RequestState --> OutputProcessor (New one for final multimodal output)
## Core Components (Ordered by Data Flow)