Facial recognition not working since 2.6.0

[stevehoek]

I have searched the existing issues, both open and closed, to make sure this is not a duplicate report.

• Yes

The bug

Running immich for over a year under Docker on Mac. Facial recognition is not running or working on photos uploaded since upgrading to 2.6.0

The OS that Immich Server is running on

Docker on macOS

Version of Immich Server

2.6.0

Version of Immich Mobile App

2.6.0

Platform with the issue

• Server
• Web
• Mobile

Device make and model

iPhone 17

Your docker-compose.yml content

#
# WARNING: Make sure to use the docker-compose.yml of the current release:
#
# https://github.com/immich-app/immich/releases/latest/download/docker-compose.yml
#
# The compose file on main may not be compatible with the latest release.
#

name: immich

services:
  immich-server:
    container_name: immich_server
    image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
    # extends:
    #   file: hwaccel.transcoding.yml
    #   service: cpu # set to one of [nvenc, quicksync, rkmpp, vaapi, vaapi-wsl] for accelerated transcoding
    volumes:
      # Do not edit the next line. If you want to change the media storage location on your system, edit the value of UPLOAD_LOCATION in the .env file
      - ${LIBRARY_LOCATION}:/usr/src/app/upload/library
      - ${UPLOAD_LOCATION}:/usr/src/app/upload/upload
      - ${THUMBS_LOCATION}:/usr/src/app/upload/thumbs
      - ${PROFILE_LOCATION}:/usr/src/app/upload/profile
      - ${VIDEO_LOCATION}:/usr/src/app/upload/encoded-video
      - ${BACKUP_LOCATION}:/usr/src/app/upload/backups
      - /etc/localtime:/etc/localtime:ro
      - nas-share-external:/mnt/media/photos:ro
    env_file:
      - .env
    ports:
      - 2283:2283
    depends_on:
      - redis
      - database
    restart: always
    healthcheck:
      disable: false
    ulimits:
      nofile:
        soft: 65536
        hard: 65536
        
  immich-machine-learning:
    container_name: immich_machine_learning
    # For hardware acceleration, add one of -[armnn, cuda, openvino] to the image tag.
    # Example tag: ${IMMICH_VERSION:-release}-cuda
    image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}
    # extends: # uncomment this section for hardware acceleration - see https://immich.app/docs/features/ml-hardware-acceleration
    #   file: hwaccel.ml.yml
    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference - use the `-wsl` version for WSL2 where applicable
    volumes:
      - model-cache:/cache
    env_file:
      - .env
    restart: always
    healthcheck:
      disable: false

  redis:
    container_name: immich_redis
    image: docker.io/valkey/valkey:8-bookworm@sha256:42cba146593a5ea9a622002c1b7cba5da7be248650cbb64ecb9c6c33d29794b1
    healthcheck:
      test: redis-cli ping || exit 1
    restart: always

  database:
    container_name: immich_postgres
    image: ghcr.io/immich-app/postgres:14-vectorchord0.3.0-pgvectors0.2.0
    environment:
      POSTGRES_PASSWORD: ${DB_PASSWORD}
      POSTGRES_USER: ${DB_USERNAME}
      POSTGRES_DB: ${DB_DATABASE_NAME}
      POSTGRES_INITDB_ARGS: '--data-checksums'
    volumes:
      # Do not edit the next line. If you want to change the database storage location on your system, edit the value of DB_DATA_LOCATION in the .env file
      - ${DB_DATA_LOCATION}:/var/lib/postgresql/data
    restart: always

  power-tools:
    container_name: immich_power_tools
    image: ghcr.io/sai80082/immich-power-tools:latest
    ports:
      - "8001:3000"
    env_file:
      - .env
    restart: always

#  immich-selfie-timelapse:
#    image: arnaudcayrol/immich-selfie-timelapse
#    container_name: immich-selfie-timelapse
#    user: 1000:1000
#    ports:
#      - "5000:5000"
#    environment:
#      - IMMICH_API_KEY=v1HJjVL9B8Vz4gGHaJ8wmzVTaVf4ZLe8ch9KPFStrQ0
#      - IMMICH_BASE_URL=http://macstudio.hoeknet.lan:2283
#    volumes:
#      - ./selfie-timelapse/config:/app/config
#      - ./selfie-timelapse/output:/app/output
#    restart: unless-stopped

volumes:
  model-cache:
  nas-share-external:
    driver_opts:
      type: cifs
      device: "//10.0.4.10/Backups/Photos/Digital"

Your .env content

# You can find documentation for all the supported env variables at https://immich.app/docs/install/environment-variables

# The location where your uploaded files are stored
LIBRARY_LOCATION=./library/
UPLOAD_LOCATION=./cache/upload/
THUMBS_LOCATION=./cache/thumbs/
PROFILE_LOCATION=./cache/profile/
VIDEO_LOCATION=./cache/encoded-video/
BACKUP_LOCATION=./cache/backups/

# The location where your database files are stored
DB_DATA_LOCATION=./postgres

# To set a timezone, uncomment the next line and change Etc/UTC to a TZ identifier from this list: https://en.wikipedia.org/wiki/List_of_tz_database_time_zones#List
TZ=America/Detroit

# The Immich version to use. You can pin this to a specific version like "v1.71.0"
IMMICH_VERSION=release

# Connection secret for postgres. You should change it to a random password
# Please use only the characters `A-Za-z0-9`, without special characters or spaces
DB_PASSWORD=postgres

# The values below this line do not need to be changed
###################################################################################
DB_USERNAME=postgres
DB_DATABASE_NAME=immich
DB_HOST=immich_postgres
DB_PORT=5432

Reproduction steps

1. Install server 2.6.0 or later
2. upload some new photos
3. see no faces recognized
   ...

Relevant log output

2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed
2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed
2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed
2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed
2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed
2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed
2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM    WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed: fetch failed



2026-03-23 07:25:46
[Nest] 7  - 03/23/2026, 7:25:46 AM   ERROR [Microservices:{"id":"66e071f8-f730-4ccc-9d0b-2978d5cb3a3b"}] Unable to run job handler (AssetDetectFaces): Error: Machine learning request '{"facial-recognition":{"detection":{"modelName":"buffalo_l","options":{"minScore":0.7}},"recognition":{"modelName":"buffalo_l"}}}' failed for all URLs

Additional information

No response

[bo0tzz]

Please post the logs of the ML container

[stevehoek]

@bo0tzz here it is. doesn't show any requests coming in; maybe I need to turn up the logging?

2026-03-19 19:34:46.994 | [03/19/26 19:34:46] INFO Starting gunicorn 25.1.0 2026-03-19 19:34:46.994 | [03/19/26 19:34:46] INFO Listening at: http://[::]:3003 (27) 2026-03-19 19:34:46.994 | [03/19/26 19:34:46] INFO Using worker: immich_ml.config.CustomUvicornWorker 2026-03-19 19:34:47.012 | [03/19/26 19:34:47] INFO Booting worker with pid: 48 2026-03-19 19:34:47.012 | [03/19/26 19:34:47] INFO Control socket listening at /usr/src/gunicorn.ctl 2026-03-19 19:34:47.125 | onnxruntime cpuid_info warning: Unknown CPU vendor. cpuinfo_vendor value: 0 2026-03-19 19:34:48.396 | [03/19/26 19:34:48] INFO Started server process [48] 2026-03-19 19:34:48.396 | [03/19/26 19:34:48] INFO Waiting for application startup. 2026-03-19 19:34:48.397 | [03/19/26 19:34:48] INFO Created in-memory cache with unloading after 300s 2026-03-19 19:34:48.397 | of inactivity. 2026-03-19 19:34:48.397 | [03/19/26 19:34:48] INFO Initialized request thread pool with 20 threads. 2026-03-19 19:34:48.398 | [03/19/26 19:34:48] INFO Application startup complete. 2026-03-19 21:06:19.384 | [03/19/26 21:06:19] INFO Loading detection model 'PP-OCRv5_mobile' to memory 2026-03-19 21:06:19.385 | [03/19/26 21:06:19] INFO Setting execution providers to 2026-03-19 21:06:19.385 | ['CPUExecutionProvider'], in descending order of 2026-03-19 21:06:19.385 | preference 2026-03-19 21:06:19.416 | [03/19/26 21:06:19] INFO Loading visual model 'ViT-B-32__openai' to memory 2026-03-19 21:06:19.417 | [03/19/26 21:06:19] INFO Setting execution providers to 2026-03-19 21:06:19.417 | ['CPUExecutionProvider'], in descending order of 2026-03-19 21:06:19.417 | preference 2026-03-19 21:06:19.905 | [03/19/26 21:06:19] INFO Loading detection model 'buffalo_l' to memory 2026-03-19 21:06:19.906 | [03/19/26 21:06:19] INFO Setting execution providers to 2026-03-19 21:06:19.906 | ['CPUExecutionProvider'], in descending order of 2026-03-19 21:06:19.906 | preference 2026-03-19 21:06:20.669 | [03/19/26 21:06:20] INFO Loading recognition model 'PP-OCRv5_mobile' to 2026-03-19 21:06:20.669 | memory 2026-03-19 21:06:20.669 | [03/19/26 21:06:20] INFO Setting execution providers to 2026-03-19 21:06:20.669 | ['CPUExecutionProvider'], in descending order of 2026-03-19 21:06:20.669 | preference 2026-03-19 21:06:20.720 | [INFO] 2026-03-19 21:06:20,719 [RapidOCR] base.py:22: Using engine_name: onnxruntime 2026-03-19 21:06:22.083 | [03/19/26 21:06:22] INFO Loading recognition model 'buffalo_l' to memory 2026-03-19 21:06:22.084 | [03/19/26 21:06:22] INFO Setting execution providers to 2026-03-19 21:06:22.084 | ['CPUExecutionProvider'], in descending order of 2026-03-19 21:06:22.084 | preference 2026-03-19 21:14:21.407 | [03/19/26 21:14:21] INFO Shutting down due to inactivity. 2026-03-19 21:14:21.414 | [03/19/26 21:14:21] INFO Shutting down 2026-03-19 21:14:21.518 | [03/19/26 21:14:21] INFO Waiting for application shutdown. 2026-03-19 21:14:21.577 | [03/19/26 21:14:21] INFO Application shutdown complete. 2026-03-19 21:14:21.577 | [03/19/26 21:14:21] INFO Finished server process [48] 2026-03-19 21:14:21.593 | [03/19/26 21:14:21] WARNING Worker (pid:48) was sent SIGINT! 2026-03-19 21:14:21.598 | [03/19/26 21:14:21] INFO Booting worker with pid: 1522 2026-03-19 21:14:21.726 | onnxruntime cpuid_info warning: Unknown CPU vendor. cpuinfo_vendor value: 0 2026-03-19 21:14:23.296 | [03/19/26 21:14:23] INFO Started server process [1522] 2026-03-19 21:14:23.296 | [03/19/26 21:14:23] INFO Waiting for application startup. 2026-03-19 21:14:23.297 | [03/19/26 21:14:23] INFO Created in-memory cache with unloading after 300s 2026-03-19 21:14:23.297 | of inactivity. 2026-03-19 21:14:23.297 | [03/19/26 21:14:23] INFO Initialized request thread pool with 20 threads. 2026-03-19 21:14:23.298 | [03/19/26 21:14:23] INFO Application startup complete. 2026-03-20 13:32:18.666 | [03/20/26 13:32:18] INFO Starting gunicorn 25.1.0 2026-03-20 13:32:18.667 | [03/20/26 13:32:18] INFO Listening at: http://[::]:3003 (27) 2026-03-20 13:32:18.667 | [03/20/26 13:32:18] INFO Using worker: immich_ml.config.CustomUvicornWorker 2026-03-20 13:32:18.681 | [03/20/26 13:32:18] INFO Control socket listening at /usr/src/gunicorn.ctl 2026-03-23 08:30:36.765 | [03/23/26 08:30:36] INFO Starting gunicorn 25.1.0 2026-03-23 08:30:36.765 | [03/23/26 08:30:36] INFO Listening at: http://[::]:3003 (27) 2026-03-23 08:30:36.765 | [03/23/26 08:30:36] INFO Using worker: immich_ml.config.CustomUvicornWorker 2026-03-23 08:30:36.783 | [03/23/26 08:30:36] INFO Control socket listening at /usr/src/gunicorn.ctl 2026-03-23 08:30:36.789 | [03/23/26 08:30:36] INFO Booting worker with pid: 48 2026-03-23 08:30:36.941 | onnxruntime cpuid_info warning: Unknown CPU vendor. cpuinfo_vendor value: 0 2026-03-23 08:30:38.818 | [03/23/26 08:30:38] INFO Started server process [48] 2026-03-23 08:30:38.819 | [03/23/26 08:30:38] INFO Waiting for application startup. 2026-03-23 08:30:38.819 | [03/23/26 08:30:38] INFO Created in-memory cache with unloading after 300s 2026-03-23 08:30:38.819 | of inactivity. 2026-03-23 08:30:38.820 | [03/23/26 08:30:38] INFO Initialized request thread pool with 20 threads. 2026-03-23 08:30:38.820 | [03/23/26 08:30:38] INFO Application startup complete.

[Mraedis]

Please restart the docker service or/and your entire Mac.

[stevehoek]

Restarting Docker seemed to take care of it; I'll keep an eye on it.

[chipmonkey]

FWIW I came here with a similar problem and the issue was too low a max memory limit on my containers. I'm running Colima on mac and the default limit was 2GB. Upping that to 16GB has resolved the issue. I'm commenting here because this is the first Github issue I saw that seems to reflect the issues I was seeing.