-------------------------------------------------------------------------------->8
[2025-07-08T02:10:20.763892000Z][inference.model-manager] Successfully initialized store
[2025-07-08T02:10:20.764188000Z][inference] 3 backends available
[2025-07-08T02:10:26.420533000Z][inference] Reconciling service state on initialization
[2025-07-08T02:10:26.420565000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2025-07-08T02:31:34.140435000Z][inference.model-manager] Successfully initialized store
[2025-07-08T02:31:34.141110000Z][inference] 3 backends available
[2025-07-08T02:31:34.928311000Z][inference] Reconciling service state on initialization
[2025-07-08T02:31:34.928800000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2025-07-08T02:48:35.585932000Z][inference.model-manager] Successfully initialized store
[2025-07-08T02:48:35.586440000Z][inference] 3 backends available
[2025-07-08T02:48:36.470198000Z][inference] Reconciling service state on initialization
[2025-07-08T02:48:36.470225000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2025-10-05T08:49:18.832010000Z][inference.model-manager] Successfully initialized store
[2025-10-05T08:49:18.832781000Z][inference] 3 backends available
[2025-10-05T08:49:19.201067000Z][inference] Reconciling service state on initialization
[2025-10-05T08:49:19.201089000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2025-10-05T08:59:05.248966000Z][inference] Running on system with 10922 MB VRAM
[2025-10-05T08:59:05.249413000Z][inference] Running on system with 16384 MB RAM
[2025-10-05T08:59:05.249494000Z][inference.model-manager] Successfully initialized store
[2025-10-05T08:59:05.249622000Z][inference] 3 backends available
[2025-10-05T08:59:23.651698000Z][inference] Reconciling service state on initialization
[2025-10-05T08:59:23.652464000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2026-05-23T10:11:32.164463000Z][inference] Running on system with 12124 MB VRAM
[2026-05-23T10:11:32.165258000Z][inference] Running on system with 16384 MB RAM
[2026-05-23T10:11:32.165743000Z][inference.model-manager] Successfully initialized store
[2026-05-23T10:11:32.166438000Z][inference] 3 backends available
[2026-05-23T10:11:42.970538000Z][inference] Reconciling service state on initialization
[2026-05-23T10:11:42.970851000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2026-05-27T10:58:18.779925000Z][inference] Running on system with 12124 MB VRAM
[2026-05-27T10:58:18.780595000Z][inference] Running on system with 16384 MB RAM
[2026-05-27T10:58:18.780725000Z][inference.model-manager] Successfully initialized store
[2026-05-27T10:58:18.781351000Z][inference] 3 backends available
[2026-05-27T10:58:19.734125000Z][inference] Reconciling service state on initialization
[2026-05-27T10:58:19.734535000Z][inference] Reconciling service state on settings change
[2026-05-27T10:58:20.977355000Z][inference] Reconciling service state on feature flag change
[2026-05-27T10:58:20.977502000Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, metal, /Applications/Docker.app/Contents/Resources/model-runner/bin, <HOME>/.docker/bin/inference/com.docker.llama-server
[2026-05-27T10:58:21.247559000Z][inference.model-manager] Listing available models
[2026-05-27T10:58:21.249159000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-27T10:58:21.488742000Z][inference.model-manager] Listing available models
[2026-05-27T10:58:21.488817000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-27T10:58:21.598019000Z][inference.inference-llama.cpp][W] failed to read current llama.cpp version: open <HOME>/.docker/bin/inference/.llamacpp_version: no such file or directory
[2026-05-27T10:58:21.598090000Z][inference.inference-llama.cpp][W] proceeding to update llama.cpp binary
[2026-05-27T10:58:21.598208000Z][inference.inference-llama.cpp] Extracting image "registry-1.docker.io/docker/docker-model-backend-llamacpp@sha256:4c1ebaef48843b9b1fd0fbd2f01547a74459d44eb32c2c3d20edeb54998133a9" to "/var/folders/sd/tydtl0cd4j756nzrywnd7xr40000gp/T/llamacpp-install2098810821"
[2026-05-27T10:58:31.116462000Z][inference.inference-llama.cpp] successfully updated llama.cpp binary
[2026-05-27T10:58:45.496872000Z][inference.inference-llama.cpp] running llama.cpp latest-metal (sha256:4c1ebaef48843b9b1fd0fbd2f01547a74459d44eb32c2c3d20edeb54998133a9) version: e365e65
[2026-05-27T10:58:46.092026000Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=true
[2026-05-27T10:58:46.092295000Z][inference][W] Backend installation failed for mlx: not implemented
[2026-05-27T10:58:46.092374000Z][inference][W] Backend installation failed for vllm: not implemented
[2026-05-27T10:59:29.982341000Z][inference.model-manager] Listing available models
[2026-05-27T10:59:29.983102000Z][inference.model-manager] Successfully listed models, count: 0
-------------------------------------------------------------------------------->8
[2026-05-29T05:48:17.076973000Z][inference] Running on system with 12124 MB VRAM
[2026-05-29T05:48:17.077982000Z][inference] Running on system with 16384 MB RAM
[2026-05-29T05:48:17.078884000Z][inference.model-manager] Successfully initialized store
[2026-05-29T05:48:17.079874000Z][inference] 3 backends available
[2026-05-29T05:48:19.627801000Z][inference] Reconciling service state on initialization
[2026-05-29T05:48:19.628783000Z][inference] Reconciling service state on settings change
[2026-05-29T05:48:19.629115000Z][inference][W] Backend installation failed for vllm: not implemented
[2026-05-29T05:48:19.629732000Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, metal, /Applications/Docker.app/Contents/Resources/model-runner/bin, <HOME>/.docker/bin/inference/com.docker.llama-server
[2026-05-29T05:48:20.706840000Z][inference.inference-llama.cpp] current llama.cpp version is already up to date
[2026-05-29T05:48:21.060102000Z][inference.model-manager] Listing available models
[2026-05-29T05:48:21.075562000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-29T05:48:21.106108000Z][inference.model-manager] Listing available models
[2026-05-29T05:48:21.112428000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-29T05:48:21.690605000Z][inference.model-manager] Listing available models
[2026-05-29T05:48:21.690748000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-29T05:48:21.895793000Z][inference.model-manager] Listing available models
[2026-05-29T05:48:21.896030000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-29T05:48:22.583736000Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=true
[2026-05-29T05:48:22.583805000Z][inference][W] Backend installation failed for mlx: not implemented
-------------------------------------------------------------------------------->8
[2026-05-31T07:36:51.299929000Z][inference] Running on system with 12124 MB VRAM
[2026-05-31T07:36:51.300588000Z][inference] Running on system with 16384 MB RAM
[2026-05-31T07:36:51.301208000Z][inference.model-manager] Successfully initialized store
[2026-05-31T07:36:51.301871000Z][inference] 3 backends available
[2026-05-31T07:36:52.257721000Z][inference] Reconciling service state on initialization
[2026-05-31T07:36:52.257810000Z][inference] Reconciling service state on settings change
[2026-05-31T07:36:52.257810000Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, metal, /Applications/Docker.app/Contents/Resources/model-runner/bin, <HOME>/.docker/bin/inference/com.docker.llama-server
[2026-05-31T07:36:53.114949000Z][inference.inference-llama.cpp] current llama.cpp version is already up to date
[2026-05-31T07:36:53.539850000Z][inference.model-manager] Listing available models
[2026-05-31T07:36:53.551198000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-31T07:36:53.562611000Z][inference.model-manager] Listing available models
[2026-05-31T07:36:53.562737000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-31T07:36:54.075780000Z][inference.model-manager] Listing available models
[2026-05-31T07:36:54.075881000Z][inference.model-manager] Successfully listed models, count: 0
[2026-05-31T07:36:54.256260000Z][inference.model-manager] Listing available models
[2026-05-31T07:36:54.256961000Z][inference.model-manager] Successfully listed models, count: 0
-------------------------------------------------------------------------------->8
[2026-06-28T06:44:53.757476000Z][inference] Running on system with 12124 MB VRAM
[2026-06-28T06:44:53.758118000Z][inference] Running on system with 16384 MB RAM
[2026-06-28T06:44:53.758539000Z][inference.model-manager] Successfully initialized store
[2026-06-28T06:44:53.759117000Z][inference] 3 backends available
[2026-06-28T06:44:55.301159000Z][inference] Reconciling service state on initialization
[2026-06-28T06:44:55.301350000Z][inference] Reconciling service state on settings change
[2026-06-28T06:44:55.301357000Z][inference][W] Backend installation failed for vllm: not implemented
[2026-06-28T06:44:55.301459000Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, metal, /Applications/Docker.app/Contents/Resources/model-runner/bin, <HOME>/.docker/bin/inference/com.docker.llama-server
[2026-06-28T06:44:56.208983000Z][inference.inference-llama.cpp] current llama.cpp version is outdated: sha256:4c1ebaef48843b9b1fd0fbd2f01547a74459d44eb32c2c3d20edeb54998133a9 vs sha256:aa3e239c5737a7fa56f3908a865eb75dfae214b9cfec2cdd929e4d5353c2d714, proceeding to update it
[2026-06-28T06:44:56.209170000Z][inference.inference-llama.cpp] Extracting image "registry-1.docker.io/docker/docker-model-backend-llamacpp@sha256:aa3e239c5737a7fa56f3908a865eb75dfae214b9cfec2cdd929e4d5353c2d714" to "/var/folders/sd/tydtl0cd4j756nzrywnd7xr40000gp/T/llamacpp-install3810574669"
[2026-06-28T06:44:56.374290000Z][inference.model-manager] Listing available models
[2026-06-28T06:44:56.375175000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T06:44:56.384133000Z][inference.model-manager] Listing available models
[2026-06-28T06:44:56.384326000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T06:44:57.020773000Z][inference.model-manager] Listing available models
[2026-06-28T06:44:57.020962000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T06:44:57.196119000Z][inference.model-manager] Listing available models
[2026-06-28T06:44:57.196374000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T06:45:33.792196000Z][inference.inference-llama.cpp] successfully updated llama.cpp binary
[2026-06-28T06:45:45.177489000Z][inference.inference-llama.cpp] running llama.cpp latest-metal (sha256:aa3e239c5737a7fa56f3908a865eb75dfae214b9cfec2cdd929e4d5353c2d714) version: ac4cdde
[2026-06-28T06:45:45.270001000Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=true
[2026-06-28T06:45:45.270075000Z][inference][W] Backend installation failed for mlx: not implemented
-------------------------------------------------------------------------------->8
[2026-06-28T08:22:28.109402000Z][inference] Running on system with 12124 MB VRAM
[2026-06-28T08:22:28.109865000Z][inference] Running on system with 16384 MB RAM
[2026-06-28T08:22:28.110162000Z][inference.model-manager] Successfully initialized store
[2026-06-28T08:22:28.111021000Z][inference] 3 backends available
[2026-06-28T08:22:28.949558000Z][inference] Reconciling service state on initialization
[2026-06-28T08:22:28.949655000Z][inference] Reconciling service state on settings change
[2026-06-28T08:22:28.949806000Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, metal, /Applications/Docker.app/Contents/Resources/model-runner/bin, <HOME>/.docker/bin/inference/com.docker.llama-server
[2026-06-28T08:22:29.599377000Z][inference.inference-llama.cpp] current llama.cpp version is already up to date
[2026-06-28T08:22:29.917827000Z][inference.model-manager] Listing available models
[2026-06-28T08:22:29.920358000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T08:22:29.940935000Z][inference.model-manager] Listing available models
[2026-06-28T08:22:29.941219000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T08:22:30.466095000Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=true
[2026-06-28T08:22:30.466170000Z][inference][W] Backend installation failed for mlx: not implemented
[2026-06-28T08:22:30.466198000Z][inference][W] Backend installation failed for vllm: not implemented
[2026-06-28T08:22:30.482233000Z][inference.model-manager] Listing available models
[2026-06-28T08:22:30.482474000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T08:22:30.642046000Z][inference.model-manager] Listing available models
[2026-06-28T08:22:30.642133000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T08:24:33.383165000Z][inference.model-manager] Listing available models
[2026-06-28T08:24:33.384491000Z][inference.model-manager] Successfully listed models, count: 0
[2026-06-28T08:33:00.030458000Z][inference.model-manager] Listing available models
[2026-06-28T08:33:00.031491000Z][inference.model-manager] Successfully listed models, count: 0
-------------------------------------------------------------------------------->8
[2026-06-28T08:33:37.106859000Z][inference.model-manager] Successfully initialized store
[2026-06-28T08:33:37.108458000Z][inference] 4 backends available
[2026-06-28T08:33:44.598053000Z][inference] Reconciling service state on initialization
[2026-06-28T08:33:44.598337000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2026-06-28T08:40:16.604113000Z][inference.model-manager] Successfully initialized store
[2026-06-28T08:40:16.604706000Z][inference] 4 backends available
[2026-06-28T08:40:17.083404000Z][inference] Reconciling service state on initialization
[2026-06-28T08:40:17.083513000Z][inference] Reconciling service state on settings change
-------------------------------------------------------------------------------->8
[2026-06-28T08:40:44.577937000Z][inference.model-manager] Successfully initialized store
[2026-06-28T08:40:44.578360000Z][inference] 4 backends available
[2026-06-28T08:40:44.777890000Z][inference] Reconciling service state on initialization
[2026-06-28T08:40:44.778232000Z][inference] Reconciling service state on settings change