helpy4/immich
1
0
Fork 0
mirror of https://github.com/immich-app/immich synced 2025-11-07 17:27:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(ml): better model unloading (#3340)

Browse source 
* restart process on inactivity

* formatting

* always update `last_called`

* load models sequentially

* renamed variable, updated docs

* formatting

* made poll env name consistent with model ttl env
This commit is contained in:
Mert 2023-11-16 21:42:44 -05:00 • committed by GitHub
parent 98f87c6548
commit a6af4892e3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 42 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

13
docs/docs/install/environment-variables.md
View file

@ -188,19 +188,18 @@ Typesense URL example JSON before encoding:
| Variable | Description | Default | Services |
| :----------------------------------------------- | :---------------------------------------------------------------- | :-----------------: | :--------------- |
| `MACHINE_LEARNING_MODEL_TTL`<sup>\*1</sup> | Inactivity time (s) before a model is unloaded (disabled if <= 0) | `0` | machine learning |
| `MACHINE_LEARNING_MODEL_TTL` | Inactivity time (s) before a model is unloaded (disabled if <= 0) | `300` | machine learning |
| `MACHINE_LEARNING_MODEL_TTL_POLL_S` | Interval (s) between checks for the model TTL (disabled if <= 0) | `10` | machine learning |
| `MACHINE_LEARNING_CACHE_FOLDER` | Directory where models are downloaded | `/cache` | machine learning |
| `MACHINE_LEARNING_REQUEST_THREADS`<sup>\*2</sup> | Thread count of the request thread pool (disabled if <= 0) | number of CPU cores | machine learning |
| `MACHINE_LEARNING_REQUEST_THREADS`<sup>\*1</sup> | Thread count of the request thread pool (disabled if <= 0) | number of CPU cores | machine learning |
| `MACHINE_LEARNING_MODEL_INTER_OP_THREADS` | Number of parallel model operations | `1` | machine learning |
| `MACHINE_LEARNING_MODEL_INTRA_OP_THREADS` | Number of threads for each model operation | `2` | machine learning |
| `MACHINE_LEARNING_WORKERS`<sup>\*3</sup> | Number of worker processes to spawn | `1` | machine learning |
| `MACHINE_LEARNING_WORKERS`<sup>\*2</sup> | Number of worker processes to spawn | `1` | machine learning |
| `MACHINE_LEARNING_WORKER_TIMEOUT` | Maximum time (s) of unresponsiveness before a worker is killed | `120` | machine learning |
\*1: This is an experimental feature. It may result in increased memory use over time when loading models repeatedly.
\*1: It is recommended to begin with this parameter when changing the concurrency levels of the machine learning service and then tune the other ones.
\*2: It is recommended to begin with this parameter when changing the concurrency levels of the machine learning service and then tune the other ones.
\*3: Since each process duplicates models in memory, changing this is not recommended unless you have abundant memory to go around.
\*2: Since each process duplicates models in memory, changing this is not recommended unless you have abundant memory to go around.
:::info