-------------------------------------------------------------------------------->8
[2025-11-28T11:07:37.537402600Z][inference] Running on system with 8192 MB VRAM
[2025-11-28T11:07:37.544664500Z][inference] Running on system with 65436 MB RAM
[2025-11-28T11:07:37.545687900Z][inference.model-manager] Successfully initialized store
[2025-11-28T11:07:37.545687900Z][inference] 2 backends available
[2025-11-28T11:07:42.965472400Z][inference] Reconciling service state on initialization
[2025-11-28T11:07:42.965472400Z][inference] Reconciling service state on settings change
[2025-11-28T11:07:42.965472400Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, cpu, C:\Program Files\Docker\Docker\resources\model-runner\bin, <HOME>\.docker\bin\inference\com.docker.llama-server.exe
[2025-11-28T11:07:43.065091300Z][inference.inference-llama.cpp][W] failed to read current llama.cpp version: open <HOME>\.docker\bin\inference\.llamacpp_version: The system cannot find the path specified.
[2025-11-28T11:07:43.065091300Z][inference.inference-llama.cpp][W] proceeding to update llama.cpp binary
[2025-11-28T11:07:43.065091300Z][inference.inference-llama.cpp] Extracting image "registry-1.docker.io/docker/docker-model-backend-llamacpp@sha256:ea16f02ab4b7ce60f05a2cc3d08d2643e53f2c7bb9187c6644fbf108d898739d" to "C:\\Users\\luctr\\AppData\\Local\\Temp\\llamacpp-install3538989501"
[2025-11-28T11:07:45.816715000Z][inference.inference-llama.cpp] successfully updated llama.cpp binary
[2025-11-28T11:07:46.103718400Z][inference.inference-llama.cpp] running llama.cpp latest-cpu (sha256:ea16f02ab4b7ce60f05a2cc3d08d2643e53f2c7bb9187c6644fbf108d898739d) version: 97d5117
[2025-11-28T11:07:46.116026400Z][inference.inference-llama.cpp][W] Failed to start sandboxed llama.cpp process to probe GPU support: unable to start sandboxed process: exec: "--list-devices": executable file not found in %PATH%
[2025-11-28T11:07:46.116026400Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=false
[2025-11-28T11:07:46.116534900Z][inference][W] Backend installation failed for vllm: not implemented
[2025-11-28T20:38:23.434667600Z][inference.model-manager] Listing available models
[2025-11-28T20:38:23.442516500Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T20:38:59.056168600Z][inference.model-manager] Listing available models
[2025-11-28T20:38:59.056684700Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T20:39:20.211650000Z][inference.model-manager] Listing available models
[2025-11-28T20:39:20.212170600Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T20:42:10.490323700Z][inference.model-manager] Listing available models
[2025-11-28T20:42:10.490867000Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T20:42:48.755486200Z][inference.model-manager] Listing available models
[2025-11-28T20:42:48.755486200Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T20:44:27.523869500Z][inference.model-manager] Listing available models
[2025-11-28T20:44:27.523869500Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T22:08:32.084572100Z][inference.model-manager] Listing available models
[2025-11-28T22:08:32.085086200Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T22:09:56.273185600Z][inference.model-manager] Listing available models
[2025-11-28T22:09:56.273185600Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-28T22:10:31.798646800Z][inference.model-manager] Listing available models
[2025-11-28T22:10:31.799153500Z][inference.model-manager] Successfully listed models, count: 0
-------------------------------------------------------------------------------->8
[2025-11-29T16:02:05.890663400Z][inference] Running on system with 8192 MB VRAM
[2025-11-29T16:02:05.899081400Z][inference] Running on system with 65436 MB RAM
[2025-11-29T16:02:05.899605400Z][inference.model-manager] Successfully initialized store
[2025-11-29T16:02:05.900129700Z][inference] 2 backends available
[2025-11-29T16:02:09.381428700Z][inference] Reconciling service state on initialization
[2025-11-29T16:02:09.381428700Z][inference] Reconciling service state on settings change
[2025-11-29T16:02:09.381428700Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, cpu, C:\Program Files\Docker\Docker\resources\model-runner\bin, <HOME>\.docker\bin\inference\com.docker.llama-server.exe
[2025-11-29T16:02:09.515248200Z][inference.inference-llama.cpp] current llama.cpp version is already up to date
[2025-11-29T16:02:10.020418300Z][inference.inference-llama.cpp][W] Failed to start sandboxed llama.cpp process to probe GPU support: unable to start sandboxed process: exec: "--list-devices": executable file not found in %PATH%
[2025-11-29T16:02:10.020418300Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=false
[2025-11-29T16:02:10.020418300Z][inference][W] Backend installation failed for vllm: not implemented
[2025-11-29T16:02:10.704937400Z][inference.model-manager] Listing available models
[2025-11-29T16:02:10.712268400Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-29T16:02:10.770804300Z][inference.model-manager] Listing available models
[2025-11-29T16:02:10.770804300Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-29T16:02:11.652245000Z][inference.model-manager] Listing available models
[2025-11-29T16:02:11.652245000Z][inference.model-manager] Successfully listed models, count: 0
[2025-11-29T16:02:48.719803200Z][inference.model-manager] Listing available models
[2025-11-29T16:02:48.721393800Z][inference.model-manager] Successfully listed models, count: 0
-------------------------------------------------------------------------------->8
[2025-12-28T19:07:56.248929100Z][inference] Running on system with 8192 MB VRAM
[2025-12-28T19:07:56.257420600Z][inference] Running on system with 65436 MB RAM
[2025-12-28T19:07:56.257947200Z][inference.model-manager] Successfully initialized store
[2025-12-28T19:07:56.257947200Z][inference] 2 backends available
[2025-12-28T19:08:01.559504000Z][inference] Reconciling service state on initialization
[2025-12-28T19:08:01.559504000Z][inference] Reconciling service state on settings change
[2025-12-28T19:08:01.559504000Z][inference.inference-llama.cpp] downloadLatestLlamaCpp: latest, cpu, C:\Program Files\Docker\Docker\resources\model-runner\bin, <HOME>\.docker\bin\inference\com.docker.llama-server.exe
[2025-12-28T19:08:01.674553500Z][inference.inference-llama.cpp] current llama.cpp version is outdated: sha256:ea16f02ab4b7ce60f05a2cc3d08d2643e53f2c7bb9187c6644fbf108d898739d vs sha256:fb231f97cf07611065835c3ee234656cf99f4969d5e3e05ca99dde6110cce39d, proceeding to update it
[2025-12-28T19:08:01.675082500Z][inference.inference-llama.cpp] Extracting image "registry-1.docker.io/docker/docker-model-backend-llamacpp@sha256:fb231f97cf07611065835c3ee234656cf99f4969d5e3e05ca99dde6110cce39d" to "C:\\Users\\luctr\\AppData\\Local\\Temp\\llamacpp-install358681044"
[2025-12-28T19:08:04.824947200Z][inference.inference-llama.cpp] successfully updated llama.cpp binary
[2025-12-28T19:08:05.337427800Z][inference.inference-llama.cpp] running llama.cpp latest-cpu (sha256:fb231f97cf07611065835c3ee234656cf99f4969d5e3e05ca99dde6110cce39d) version: 34ce48d
[2025-12-28T19:08:05.338847100Z][inference.model-manager] Listing available models
[2025-12-28T19:08:05.348192600Z][inference.model-manager] Successfully listed models, count: 0
[2025-12-28T19:08:05.350370000Z][inference.model-manager] Listing available models
[2025-12-28T19:08:05.350896600Z][inference.model-manager] Successfully listed models, count: 0
[2025-12-28T19:08:05.354080100Z][inference.inference-llama.cpp][W] Failed to start sandboxed llama.cpp process to probe GPU support: unable to start sandboxed process: exec: "--list-devices": executable file not found in %PATH%
[2025-12-28T19:08:05.354080100Z][inference.inference-llama.cpp] installed llama-server with gpuSupport=false
[2025-12-28T19:08:05.354080100Z][inference][W] Backend installation failed for vllm: not implemented