LLM/docling-serve
1
0
Fork 0
mirror of https://github.com/docling-project/docling-serve.git synced 2025-11-29 08:33:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: workers without shared models and convert params (#304)

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-08-07 11:16:06 +02:00
committed by GitHub
parent fd1b987e8d
commit db3fdb5bc1
5 changed files with 602 additions and 621 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/configuration.md
View File

@@ -66,6 +66,7 @@ The following table describes the options to configure the Docling Serve local e
| ENV | Default | Description |
|-----|---------|-------------|
| `DOCLING_SERVE_ENG_LOC_NUM_WORKERS` | 2 | Number of workers/threads processing the incoming tasks. |
| `DOCLING_SERVE_ENG_LOC_SHARE_MODELS` | False | If true, each process will share the same models among all thread workers. Otherwise, one instance of the models is allocated for each worker thread. |
#### KFP engine