2026-04-23 11:55:17.619 [Info] (WebSocket) New connection from: 127.0.0.1 (id: 17)
2026-04-23 12:50:30.136 [Info] (Server) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:50:30.139 [Info] (LlamaCpp) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:50:30.141 [Info] (LlamaCpp) Starting llama-server...
2026-04-23 12:50:30.175 [Info] (ProcessManager) Process started successfully, PID: 34618
2026-04-23 12:50:30.221 [Info] (Process) dyld[34618]: Library not loaded: @rpath/libllama-common.0.dylib
2026-04-23 12:50:30.221 [Info] (Process)   Referenced from: <1788B481-CB66-3D37-8BA9-E3171CA7DAEE> /Users/Myname/Downloads/llama-b8840/llama-server
2026-04-23 12:50:30.221 [Info] (Process)   Reason: tried: '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open()), '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open())
2026-04-23 12:50:30.350 [Error] (WrappedServer) llama-server process has terminated with exit code: -1
2026-04-23 12:50:30.351 [Error] (WrappedServer) This usually means:
2026-04-23 12:50:30.351 [Error] (WrappedServer)   - Missing required drivers or dependencies
2026-04-23 12:50:30.351 [Error] (WrappedServer)   - Incompatible model file
2026-04-23 12:50:30.351 [Error] (WrappedServer)   - Try running the server manually to see the actual error
2026-04-23 12:50:38.584 [Warn] (ProcessManager) Process did not respond to SIGTERM, using SIGKILL
2026-04-23 12:50:38.584 [Info] (ProcessManager) Process terminated, waiting for GPU driver cleanup...
2026-04-23 12:50:40.646 [Error] (Router) Backend load failed: llama-server failed to start
2026-04-23 12:50:40.646 [Warn] (Router) Load failed with non-file-not-found error, evicting all models and retrying...
2026-04-23 12:50:40.647 [Info] (Router) Evicting all models (0 total)
2026-04-23 12:50:40.647 [Info] (Router) All models evicted
2026-04-23 12:50:40.647 [Info] (LlamaCpp) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:50:40.648 [Info] (LlamaCpp) Starting llama-server...
2026-04-23 12:50:40.649 [Info] (ProcessManager) Process started successfully, PID: 34621
2026-04-23 12:50:40.653 [Info] (Process) dyld[34621]: Library not loaded: @rpath/libllama-common.0.dylib
2026-04-23 12:50:40.653 [Info] (Process)   Referenced from: <1788B481-CB66-3D37-8BA9-E3171CA7DAEE> /Users/Myname/Downloads/llama-b8840/llama-server
2026-04-23 12:50:40.653 [Info] (Process)   Reason: tried: '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open()), '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open())
2026-04-23 12:50:40.815 [Error] (WrappedServer) llama-server process has terminated with exit code: -1
2026-04-23 12:50:40.815 [Error] (WrappedServer) This usually means:
2026-04-23 12:50:40.815 [Error] (WrappedServer)   - Missing required drivers or dependencies
2026-04-23 12:50:40.815 [Error] (WrappedServer)   - Incompatible model file
2026-04-23 12:50:40.816 [Error] (WrappedServer)   - Try running the server manually to see the actual error
2026-04-23 12:50:49.155 [Warn] (ProcessManager) Process did not respond to SIGTERM, using SIGKILL
2026-04-23 12:50:49.156 [Info] (ProcessManager) Process terminated, waiting for GPU driver cleanup...
2026-04-23 12:50:51.231 [Error] (Router) Retry also failed: llama-server failed to start
2026-04-23 12:50:51.231 [Info] (LlamaCpp) Unloading model...
2026-04-23 12:50:51.231 [Info] (LlamaCpp) Unloading model...
2026-04-23 12:50:51.231 [Error] (Router) Failed to load model: llama-server failed to start
2026-04-23 12:50:51.231 [Error] (Server) Failed to load model: llama-server failed to start
2026-04-23 12:50:51.231 [Error] (Server) Error 500: POST /api/v1/load
2026-04-23 12:53:55.197 [Info] (WebSocket) New connection from: 127.0.0.1 (id: 18)
2026-04-23 12:53:57.340 [Info] (Server) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:53:57.340 [Info] (LlamaCpp) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:53:57.341 [Info] (LlamaCpp) Starting llama-server...
2026-04-23 12:53:57.348 [Info] (ProcessManager) Process started successfully, PID: 34669
2026-04-23 12:53:57.353 [Info] (Process) dyld[34669]: Library not loaded: @rpath/libllama-common.0.dylib
2026-04-23 12:53:57.353 [Info] (Process)   Referenced from: <1788B481-CB66-3D37-8BA9-E3171CA7DAEE> /Users/Myname/Downloads/llama-b8840/llama-server
2026-04-23 12:53:57.353 [Info] (Process)   Reason: tried: '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open()), '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open())
2026-04-23 12:53:57.516 [Error] (WrappedServer) llama-server process has terminated with exit code: -1
2026-04-23 12:53:57.516 [Error] (WrappedServer) This usually means:
2026-04-23 12:53:57.516 [Error] (WrappedServer)   - Missing required drivers or dependencies
2026-04-23 12:53:57.517 [Error] (WrappedServer)   - Incompatible model file
2026-04-23 12:53:57.517 [Error] (WrappedServer)   - Try running the server manually to see the actual error
2026-04-23 12:54:05.970 [Warn] (ProcessManager) Process did not respond to SIGTERM, using SIGKILL
2026-04-23 12:54:05.970 [Info] (ProcessManager) Process terminated, waiting for GPU driver cleanup...
2026-04-23 12:54:08.042 [Error] (Router) Backend load failed: llama-server failed to start
2026-04-23 12:54:08.042 [Warn] (Router) Load failed with non-file-not-found error, evicting all models and retrying...
2026-04-23 12:54:08.042 [Info] (Router) Evicting all models (0 total)
2026-04-23 12:54:08.042 [Info] (Router) All models evicted
2026-04-23 12:54:08.042 [Info] (LlamaCpp) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:54:08.042 [Info] (LlamaCpp) Starting llama-server...
2026-04-23 12:54:08.043 [Info] (ProcessManager) Process started successfully, PID: 34675
2026-04-23 12:54:08.046 [Info] (Process) dyld[34675]: Library not loaded: @rpath/libllama-common.0.dylib
2026-04-23 12:54:08.046 [Info] (Process)   Referenced from: <1788B481-CB66-3D37-8BA9-E3171CA7DAEE> /Users/Myname/Downloads/llama-b8840/llama-server
2026-04-23 12:54:08.046 [Info] (Process)   Reason: tried: '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open()), '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open())
2026-04-23 12:54:08.215 [Error] (WrappedServer) llama-server process has terminated with exit code: -1
2026-04-23 12:54:08.215 [Error] (WrappedServer) This usually means:
2026-04-23 12:54:08.215 [Error] (WrappedServer)   - Missing required drivers or dependencies
2026-04-23 12:54:08.215 [Error] (WrappedServer)   - Incompatible model file
2026-04-23 12:54:08.215 [Error] (WrappedServer)   - Try running the server manually to see the actual error
2026-04-23 12:54:11.912 [Info] (Server) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:54:11.912 [Info] (Router) Another load is in progress, waiting...
2026-04-23 12:54:16.585 [Warn] (ProcessManager) Process did not respond to SIGTERM, using SIGKILL
2026-04-23 12:54:16.586 [Info] (ProcessManager) Process terminated, waiting for GPU driver cleanup...
2026-04-23 12:54:18.660 [Error] (Router) Retry also failed: llama-server failed to start
2026-04-23 12:54:18.660 [Info] (LlamaCpp) Unloading model...
2026-04-23 12:54:18.660 [Info] (LlamaCpp) Unloading model...
2026-04-23 12:54:18.661 [Error] (Router) Failed to load model: llama-server failed to start
2026-04-23 12:54:18.661 [Error] (Server) Failed to load model: llama-server failed to start
2026-04-23 12:54:18.661 [Error] (Server) Loading model: Gemma-4-E2B-it-GGUF (checkpoint: unsloth/gemma-4-E2B-it-GGUF:Q4_K_M, recipe: llamacpp, type: llm, device: gpu)
2026-04-23 12:54:18.661 [Info] (LlamaCpp) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:54:18.661 [Info] (LlamaCpp) Starting llama-server...
2026-04-23 12:54:18.662 [Info] (ProcessManager) Process started successfully, PID: 34681
2026-04-23 12:54:18.665 [Info] (Process) dyld[34681]: Library not loaded: @rpath/libllama-common.0.dylib
2026-04-23 12:54:18.665 [Info] (Process)   Referenced from: <1788B481-CB66-3D37-8BA9-E3171CA7DAEE> /Users/Myname/Downloads/llama-b8840/llama-server
2026-04-23 12:54:18.665 [Info] (Process)   Reason: tried: '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open()), '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open())
2026-04-23 12:54:18.836 [Error] (WrappedServer) llama-server process has terminated with exit code: -1
2026-04-23 12:54:18.836 [Error] (WrappedServer) This usually means:
2026-04-23 12:54:18.836 [Error] (WrappedServer)   - Missing required drivers or dependencies
2026-04-23 12:54:18.836 [Error] (WrappedServer)   - Incompatible model file
2026-04-23 12:54:18.836 [Error] (WrappedServer)   - Try running the server manually to see the actual error
2026-04-23 12:54:27.253 [Warn] (ProcessManager) Process did not respond to SIGTERM, using SIGKILL
2026-04-23 12:54:27.253 [Info] (ProcessManager) Process terminated, waiting for GPU driver cleanup...
2026-04-23 12:54:29.314 [Error] (Router) Backend load failed: llama-server failed to start
2026-04-23 12:54:29.314 [Warn] (Router) Load failed with non-file-not-found error, evicting all models and retrying...
2026-04-23 12:54:29.314 [Info] (Router) Evicting all models (0 total)
2026-04-23 12:54:29.314 [Info] (Router) All models evicted
2026-04-23 12:54:29.314 [Info] (LlamaCpp) Loading model: Gemma-4-E2B-it-GGUF
2026-04-23 12:54:29.314 [Info] (LlamaCpp) Starting llama-server...
2026-04-23 12:54:29.316 [Info] (ProcessManager) Process started successfully, PID: 34685
2026-04-23 12:54:29.320 [Info] (Process) dyld[34685]: Library not loaded: @rpath/libllama-common.0.dylib
2026-04-23 12:54:29.321 [Info] (Process)   Referenced from: <1788B481-CB66-3D37-8BA9-E3171CA7DAEE> /Users/Myname/Downloads/llama-b8840/llama-server
2026-04-23 12:54:29.321 [Info] (Process)   Reason: tried: '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open()), '/Users/Myname/Downloads/llama-b8840/libllama-common.0.dylib' (file system sandbox blocked open())
2026-04-23 12:54:29.488 [Error] (WrappedServer) llama-server process has terminated with exit code: -1
2026-04-23 12:54:29.488 [Error] (WrappedServer) This usually means:
2026-04-23 12:54:29.488 [Error] (WrappedServer)   - Missing required drivers or dependencies
2026-04-23 12:54:29.488 [Error] (WrappedServer)   - Incompatible model file
2026-04-23 12:54:29.488 [Error] (WrappedServer)   - Try running the server manually to see the actual error
2026-04-23 12:54:37.883 [Warn] (ProcessManager) Process did not respond to SIGTERM, using SIGKILL
2026-04-23 12:54:37.884 [Info] (ProcessManager) Process terminated, waiting for GPU driver cleanup...
2026-04-23 12:54:39.955 [Error] (Router) Retry also failed: llama-server failed to start
2026-04-23 12:54:39.955 [Info] (LlamaCpp) Unloading model...
2026-04-23 12:54:39.955 [Info] (LlamaCpp) Unloading model...
2026-04-23 12:54:39.955 [Error] (Router) Failed to load model: llama-server failed to start
2026-04-23 12:54:39.956 [Error] (Server) Failed to load model: llama-server failed to start
2026-04-23 12:54:39.956 [Error] (Server) Error 500: POST /api/v1/load