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

[Doc] Fix GPU Worker count in Process Count Summary (#36000)

Browse Source 
Signed-off-by: simone-dotolo <simonedotolo@libero.it>
Signed-off-by: simone-dotolo <84937474+simone-dotolo@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
simone-dotolo
2026-03-04 18:03:14 +01:00
committed by GitHub
parent 289fc48ab7
commit e86221deb6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/design/arch_overview.md
View File

@@ -122,7 +122,7 @@ For a deployment with `N` GPUs, `TP` tensor parallel size, `DP` data parallel si
|---|---|---|
| API Server | `A` (default `DP`) | Handles HTTP requests and input processing |
| Engine Core | `DP` (default 1) | Scheduler and KV cache management |
| GPU Worker | `N` (= `DP x TP`) | One per GPU, executes model forward passes |
| GPU Worker | `N` (= `DP x PP x TP`) | One per GPU, executes model forward passes |
| DP Coordinator | 1 if `DP > 1`, else 0 | Load balancing across DP ranks |
| **Total** | **`A + DP + N` (+ 1 if DP > 1)** | |