0
Maestro: [Pipeline] Planning error: llama-server exited with code 127:
App: Maestro (Maestro.git)
Repo: https://github.com/Blizaine/Maestro.git
Generated: 2026-09-03T22:19:25.118Z
Pinokio: 8.2.0
Platform: linux x64
Node: v22.21.1
Summary
System
{
"pinokio": {
"version": "8.2.0",
"node": "v22.21.1",
"platform": "linux",
"arch": "x64"
},
"hardware": {
"gpu": "nvidia",
"gpu_model": "ga102 [geforce rtx 3090]",
"ram_gb": 94,
"vram_gb": 24,
"gpu_driver": "580.173.02",
"gpu_target": "sm_86"
},
"os": {
"platform": "linux",
"distro": "Pop",
"release": "24.04 LTS",
"codename": "noble",
"kernel": "7.0.11-76070011-generic",
"arch": "x64",
"uefi": true
},
"system": {
"manufacturer": "ASUS",
"model": "System Product Name",
"version": "System Version",
"virtual": false
},
"cpu": {
"manufacturer": "Intel",
"brand": "Core™ i9-14900K",
"vendor": "Intel",
"family": "6",
"model": "183",
"stepping": "1",
"speed": 1.39,
"speedMin": 0.8,
"speedMax": 5.5,
"cores": 32,
"physicalCores": 24,
"processors": 1,
"performanceCores": 8,
"efficiencyCores": 16,
"virtualization": true,
"cache": {
"l1d": 917504,
"l1i": 1048576,
"l2": 33554432,
"l3": 37748736
}
},
"memory": {
"total": 100907937792,
"free": 82105348096,
"used": 18802589696,
"active": 15645405184,
"available": 85262532608,
"buffers": 8253440,
"cached": 9671798784,
"slab": 597200896,
"buffcache": 10277253120,
"swaptotal": 17179865088,
"swapused": 0,
"swapfree": 17179865088
},
"gpus": [
{
"model": "ga102 [geforce rtx 3090]"
}
],
"graphics": {
"controllers": [
{
"vendor": "NVIDIA Corporation",
"model": "GA102 [GeForce RTX 3090]",
"bus": "Onboard",
"vram": 24576,
"vramDynamic": false,
"driverVersion": "580.173.02"
}
],
"displays": [
{
"model": "LG TV",
"main": true,
"builtin": false,
"connection": "HDMI-0",
"currentResX": 3840,
"currentResY": 2160,
"resolutionX": 3840,
"resolutionY": 2160,
"pixelDepth": 24,
"currentRefreshRate": 60
}
]
},
"diagnostics": {
"platform": "linux",
"arch": "x64",
"running": {
"/home/professorjones/pinokio/api/Maestro.git/start.js": true
},
"home": "/home/professorjones/pinokio",
"vars": {
"pip": {
"install": {
"torch": "pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu"
}
}
},
"memory": {
"local": {
"/home/professorjones/pinokio/api/Maestro.git/start.js": {
"url": "http://127.0.0.1:42003"
}
},
"global": {},
"rpc": {
"/home/professorjones/pinokio/api/stabledaw.pinokio-2/install.js": {
"when": "{{!exists('models/stable-audio-3-small-music')}}",
"method": "shell.run",
"params": {
"path": "models",
"message": [
"node -e \"require('fs').symlinkSync(require('path').resolve('stable-audio-3-small'),'stable-audio-3-small-music','junction')\""
]
}
},
"/home/professorjones/pinokio/api/stabledaw.pinokio-2/start.js": {
"method": "local.set",
"params": {
"url": "{{input.event[1]}}"
}
},
"/home/professorjones/pinokio/api/wan2.git/start.js": {
"method": "local.set",
"params": {
"url": "{{input.event[0]}}"
}
},
"/home/professorjones/pinokio/api/Maestro.git/start.js": {
"method": "local.set",
"params": {
"url": "{{input.event[1]}}"
}
},
"/home/professorjones/pinokio/api/Maestro.git/update.js": {
"method": "log",
"params": {
"raw": "Already up to date — no new commits pulled. Skipped dependency install and UI rebuild."
},
"next": null
},
"/home/professorjones/pinokio/api/Maestro.git/install.js": {
"method": "input",
"params": {
"title": "Installation completed",
"description": "Click \"Start\" to get started"
}
},
"/home/professorjones/pinokio/api/Maestro.git/torch.js": {
"method": "fs.write",
"params": {
"path": "app/env/.maestro_flash_2_7_4_v1.installed",
"text": "Maestro CUDA 12.8 legacy FlashAttention wheel installed. Delete this file and run Update to repair it."
}
}
},
"input": {
"/home/professorjones/pinokio/api/stabledaw.pinokio-2/install.js": {
"id": "2a3b066f-df40-47bb-85e0-787b4232be1d",
"response": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && node -e \"require('fs').renameSync('model.safetensors','stable-audio-3-small-ARC.safetensors')\"\r\n(base) <<PINOKIO_SHELL>>",
"stdout": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && node -e \"require('fs').renameSync('model.safetensors','stable-audio-3-small-ARC.safetensors')\"\r\n(base) <<PINOKIO_SHELL>>"
},
"/home/professorjones/pinokio/api/stabledaw.pinokio-2/start.js": {
"id": "c0809dc1-2b15-436f-9ca9-e8abea368f6b",
"response": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && npx vite --host 127.0.0.1 --config ../../vite.launcher.config.mjs\r\n\r\n VITE v6.4.2 ready in 218 ms\r\n\r\n ➜ Local: http://127.0.0.1:5173/\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n",
"stdout": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && npx vite --host 127.0.0.1 --config ../../vite.launcher.config.mjs\r\n\r\n VITE v6.4.2 ready in 218 ms\r\n\r\n ➜ Local: http://127.0.0.1:5173/\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n",
"event": [
"http://127.0.0.1:5173/",
"http://127.0.0.1:5173/"
]
},
"/home/professorjones/pinokio/api/wan2.git/start.js": {
"id": "a07660ad-9473-4238-a002-63539a48ec96",
"response": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /home/professorjones/pinokio/api/wan2.git/app/env/bin/activate /home/professorjones/pinokio/api/wan2.git/app/env ; . bluefairy-activate && python wgp.py --multiple-images \r\n==> bluefairy active: uv/npm/bun protection enabled\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\n[Quanto][INT8] Injected int8 kernels ACTIVE (backend=triton).\r\nLoaded plugin: Motion Designer (from motion_designer)\r\n* Running on local URL: http://127.0.0.1:42003",
"stdout": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /home/professorjones/pinokio/api/wan2.git/app/env/bin/activate /home/professorjones/pinokio/api/wan2.git/app/env ; . bluefairy-activate && python wgp.py --multiple-images \r\n==> bluefairy active: uv/npm/bun protection enabled\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\n[Quanto][INT8] Injected int8 kernels ACTIVE (backend=triton).\r\nLoaded plugin: Motion Designer (from motion_designer)\r\n* Running on local URL: http://127.0.0.1:42003",
"event": [
"http://127.0.0.1:42003"
]
},
"/home/professorjones/pinokio/api/Maestro.git/start.js": {
"id": "299a8343-867e-4407-919b-6fe477d7121f",
"response": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /home/professorjones/pinokio/api/Maestro.git/app/env/bin/activate /home/professorjones/pinokio/api/Maestro.git/app/env && python launch.py \r\n[Maestro] Installing download stall protection...\r\n[safe_download] tqdm download hook installed\r\n[Maestro] Importing WanGP engine...\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\n[Runtime] Python 3.10.20 | PyTorch 2.7.0+cu128 | CUDA 12.8 | NVIDIA GeForce RTX 3090 (sm_86)\r\n[Runtime] Kernels: Triton=ready (3.3.0), SageAttention=ready, Lightx2v NVFP4=missing, FlashAttention=ready, H3 Sol Engine=unavailable in this runtime\r\n[GuideLoader] Guide not found: prompt_enhancer/dramabox_speech_rules.md\r\n[GuideLoader] Guide not found: prompt_enhancer/dramabox_dialogue_rules.md\r\n[Quanto][INT8] Injected int8 kernels ACTIVE (backend=triton).\r\n[Maestro] WanGP loaded: 197 models available\r\n[Workspace] Active workspace: default (outputs)\r\n[Maestro] Gradio classic UI mounted at /classic\r\n[Maestro] React UI serving from /home/professorjones/pinokio/api/Maestro.git/ui/dist\r\n\r\n==================================================\r\n Maestro UI: http://127.0.0.1:42003/\r\n Classic UI: http://127.0.0.1:42003/classic/\r\n API docs: http://127.0.0.1:42003/docs\r\n==================================================",
"stdout": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /home/professorjones/pinokio/api/Maestro.git/app/env/bin/activate /home/professorjones/pinokio/api/Maestro.git/app/env && python launch.py \r\n[Maestro] Installing download stall protection...\r\n[safe_download] tqdm download hook installed\r\n[Maestro] Importing WanGP engine...\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\n[Runtime] Python 3.10.20 | PyTorch 2.7.0+cu128 | CUDA 12.8 | NVIDIA GeForce RTX 3090 (sm_86)\r\n[Runtime] Kernels: Triton=ready (3.3.0), SageAttention=ready, Lightx2v NVFP4=missing, FlashAttention=ready, H3 Sol Engine=unavailable in this runtime\r\n[GuideLoader] Guide not found: prompt_enhancer/dramabox_speech_rules.md\r\n[GuideLoader] Guide not found: prompt_enhancer/dramabox_dialogue_rules.md\r\n[Quanto][INT8] Injected int8 kernels ACTIVE (backend=triton).\r\n[Maestro] WanGP loaded: 197 models available\r\n[Workspace] Active workspace: default (outputs)\r\n[Maestro] Gradio classic UI mounted at /classic\r\n[Maestro] React UI serving from /home/professorjones/pinokio/api/Maestro.git/ui/dist\r\n\r\n==================================================\r\n Maestro UI: http://127.0.0.1:42003/\r\n Classic UI: http://127.0.0.1:42003/classic/\r\n API docs: http://127.0.0.1:42003/docs\r\n==================================================",
"event": [
"http://127.0.0.1:42003",
"http://127.0.0.1:42003"
]
},
"/home/professorjones/pinokio/api/Maestro.git/update.js": null,
"/home/professorjones/pinokio/api/Maestro.git/install.js": {
"id": "06ef35d1-25a4-4907-aa7d-e7ccf680705c",
"response": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && npm run build\r\n\r\n> ui@0.0.0 build\r\n> tsc -b && vite build\r\n\r\nvite v7.3.2 building client environment for production...\r\n✓ 1808 modules transformed.\r\ndist/index.html 5.16 kB │ gzip: 2.23 kB\r\ndist/assets/index-C2jY6mpl.css 82.97 kB │ gzip: 13.67 kB\r\ndist/assets/index-TuAuLLQ-.js 1,004.12 kB │ gzip: 260.77 kB\r\n\r\n(!) Some chunks are larger than 500 kB after minification. Consider:\r\n- Using dynamic import() to code-split the application\r\n- Use build.rollupOptions.output.manualChunks to improve chunking: https://rollupjs.org/configuration-options/#output-manualchunks\r\n- Adjust chunk size limit for this warning via build.chunkSizeWarningLimit.\r\n✓ built in 1.73s\r\n(base) <<PINOKIO_SHELL>>",
"stdout": "<<PINOKIO_SHELL>>eval \"$(conda shell.bash hook)\" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && npm run build\r\n\r\n> ui@0.0.0 build\r\n> tsc -b && vite build\r\n\r\nvite v7.3.2 building client environment for production...\r\n✓ 1808 modules transformed.\r\ndist/index.html 5.16 kB │ gzip: 2.23 kB\r\ndist/assets/index-C2jY6mpl.css 82.97 kB │ gzip: 13.67 kB\r\ndist/assets/index-TuAuLLQ-.js 1,004.12 kB │ gzip: 260.77 kB\r\n\r\n(!) Some chunks are larger than 500 kB after minification. Consider:\r\n- Using dynamic import() to code-split the application\r\n- Use build.rollupOptions.output.manualChunks to improve chunking: https://rollupjs.org/configuration-options/#output-manualchunks\r\n- Adjust chunk size limit for this warning via build.chunkSizeWarningLimit.\r\n✓ built in 1.73s\r\n(base) <<PINOKIO_SHELL>>"
}
},
"args": {
"/home/professorjones/pinokio/api/stabledaw.pinokio-2/install.js": {},
"/home/professorjones/pinokio/api/stabledaw.pinokio-2/start.js": {},
"/home/professorjones/pinokio/api/wan2.git/start.js": {},
"/home/professorjones/pinokio/api/Maestro.git/start.js": {},
"/home/professorjones/pinokio/api/Maestro.git/update.js": {},
"/home/professorjones/pinokio/api/Maestro.git/install.js": {},
"/home/professorjones/pinokio/api/Maestro.git/torch.js": {
"venv": "env",
"path": "app",
"xformers": true
}
}
},
"procs": {},
"gpu": "nvidia",
"gpus": [
{
"name": "nvidia corporation",
"model": "ga102 [geforce rtx 3090]",
"driver": "580.173.02"
}
],
"gpu_model": "ga102 [geforce rtx 3090]",
"gpu_driver": "580.173.02",
"gpu_target": "sm_86",
"ram": 94,
"vram": 24,
"version": "8.2.0",
"system": {
"manufacturer": "ASUS",
"model": "System Product Name",
"version": "System Version",
"serial": "-",
"uuid": "",
"sku": "-",
"virtual": false
},
"audio": [
{
"id": "00:1f.3",
"name": "Device 8694",
"manufacturer": "ASUSTeK Computer Inc.",
"revision": "11",
"driver": "snd_hda_intel",
"default": null,
"channel": "PCIe",
"type": "",
"in": null,
"out": null,
"status": "online"
},
{
"id": "01:00.1",
"name": "GA102 High Definition Audio Controller",
"manufacturer": "eVga.com. Corp.",
"revision": "a1",
"driver": "snd_hda_intel",
"default": null,
"channel": "PCIe",
"type": "Sound Driver",
"in": null,
"out": null,
"status": "online"
}
],
"osInfo": {
"platform": "linux",
"distro": "Pop",
"release": "24.04 LTS",
"codename": "noble",
"kernel": "7.0.11-76070011-generic",
"arch": "x64",
"hostname": "pop-os",
"fqdn": "pop-os",
"codepage": "UTF-8",
"logofile": "pop",
"serial": "4dc60b4ca97fbedfd61c98c96919c3e0",
"build": "",
"servicepack": "",
"uefi": true
},
"cpu": {
"manufacturer": "Intel",
"brand": "Core™ i9-14900K",
"vendor": "Intel",
"family": "6",
"model": "183",
"stepping": "1",
"revision": "",
"voltage": "",
"speed": 1.39,
"speedMin": 0.8,
"speedMax": 5.5,
"governor": "powersave",
"cores": 32,
"physicalCores": 24,
"performanceCores": 8,
"efficiencyCores": 16,
"processors": 1,
"socket": "",
"flags": "fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize pconfig arch_lbr ibt flush_l1d arch_capabilities",
"virtualization": true,
"cache": {
"l1d": 917504,
"l1i": 1048576,
"l2": 33554432,
"l3": 37748736
}
},
"mem": {
"total": 100907937792,
"free": 82105348096,
"used": 18802589696,
"active": 15645405184,
"available": 85262532608,
"buffers": 8253440,
"cached": 9671798784,
"slab": 597200896,
"buffcache": 10277253120,
"reclaimable": 211464192,
"swaptotal": 17179865088,
"swapused": 0,
"swapfree": 17179865088,
"writeback": 0,
"dirty": 30142464
},
"shell": "/bin/bash",
"graphics": {
"controllers": [
{
"vendor": "NVIDIA Corporation",
"subVendor": "eVga.com. Corp.",
"model": "GA102 [GeForce RTX 3090]",
"bus": "Onboard",
"busAddress": "01:00.0",
"vram": 24576,
"vramDynamic": false,
"pciID": "",
"driverVersion": "580.173.02",
"subDeviceId": "0x39823842",
"name": "NVIDIA GeForce RTX 3090",
"pciBus": "00000000:01:00.0",
"fanSpeed": 38,
"memoryTotal": 24576,
"memoryUsed": 1138,
"memoryFree": 22984,
"utilizationGpu": 7,
"utilizationMemory": 7,
"temperatureGpu": 33,
"powerDraw": 45.95,
"powerLimit": 420,
"clockCore": 210,
"clockMemory": 405
}
],
"displays": [
{
"vendor": "",
"model": "LG TV",
"deviceName": "",
"main": true,
"builtin": false,
"connection": "HDMI-0",
"sizeX": 1600,
"sizeY": 900,
"pixelDepth": 24,
"resolutionX": 3840,
"resolutionY": 2160,
"currentResX": 3840,
"currentResY": 2160,
"positionX": 0,
"positionY": 0,
"currentRefreshRate": 60
}
]
}
}
}
Logs
logs/api/start.js/1788473462999
Source: api / start.js
Lines: 96 total, last 96 included
[api shell.run]
<<PINOKIO_SHELL>>eval "$(conda shell.bash hook)" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /home/professorjones/pinokio/api/Maestro.git/app/env/bin/activate /home/professorjones/pinokio/api/Maestro.git/app/env && python launch.py
[Maestro] Installing download stall protection...
[safe_download] tqdm download hook installed
[Maestro] Importing WanGP engine...
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
[Runtime] Python 3.10.20 | PyTorch 2.7.0+cu128 | CUDA 12.8 | NVIDIA GeForce RTX 3090 (sm_86)
[Runtime] Kernels: Triton=ready (3.3.0), SageAttention=ready, Lightx2v NVFP4=missing, FlashAttention=ready, H3 Sol Engine=unavailable in this runtime
[GuideLoader] Guide not found: prompt_enhancer/dramabox_speech_rules.md
[GuideLoader] Guide not found: prompt_enhancer/dramabox_dialogue_rules.md
[Quanto][INT8] Injected int8 kernels ACTIVE (backend=triton).
[Maestro] WanGP loaded: 197 models available
[Workspace] Active workspace: default (outputs)
[Maestro] Gradio classic UI mounted at /classic
[Maestro] React UI serving from /home/professorjones/pinokio/api/Maestro.git/ui/dist
==================================================
Maestro UI: http://127.0.0.1:42003/
Classic UI: http://127.0.0.1:42003/classic/
API docs: http://127.0.0.1:42003/docs
==================================================
INFO: Started server process [73784]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:42003 (Press CTRL+C to quit)
INFO: 127.0.0.1:59526 - "GET / HTTP/1.1" 200 OK
INFO: 127.0.0.1:59526 - "GET /assets/index-TuAuLLQ-.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:59534 - "GET /assets/index-C2jY6mpl.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:59536 - "GET /api/v1/presets HTTP/1.1" 200 OK
INFO: 127.0.0.1:59534 - "GET /api/v1/loras/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:59526 - "GET /api/v1/loras/ltx2_22B_distilled_1_1/details HTTP/1.1" 200 OK
INFO: 127.0.0.1:59550 - "GET /api/v1/system/preflight HTTP/1.1" 200 OK
INFO: 127.0.0.1:59550 - "GET /api/v1/h3-window-overrides HTTP/1.1" 200 OK
INFO: 127.0.0.1:59526 - "GET /api/v1/model-visibility HTTP/1.1" 200 OK
INFO: 127.0.0.1:59546 - "GET /api/v1/director/queue HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "GET /api/v1/services-config HTTP/1.1" 200 OK
INFO: 127.0.0.1:59536 - "GET /api/v1/workspaces HTTP/1.1" 200 OK
INFO: 127.0.0.1:59526 - "GET /api/v1/system-config HTTP/1.1" 200 OK
INFO: 127.0.0.1:59534 - "GET /api/v1/models HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "GET /api/v1/llm/models HTTP/1.1" 200 OK
INFO: 127.0.0.1:59550 - "GET /api/v1/system-detect HTTP/1.1" 200 OK
INFO: 127.0.0.1:59534 - "GET /api/v1/model-options/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:59546 - "GET /api/v1/loras/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:59526 - "GET /api/v1/defaults/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:59536 - "GET /api/v1/director/pipelines HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "GET /api/v1/loras/installed HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "POST /api/v1/loras/check-updates HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "GET /api/v1/director/queue HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "GET /api/v1/model-options/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:59536 - "GET /api/v1/model-options/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:59536 - "GET /api/v1/defaults/flux2_klein_9b HTTP/1.1" 200 OK
INFO: 127.0.0.1:41764 - "GET /api/v1/defaults/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:37098 - "GET /api/v1/model-options/flux2_klein_9b HTTP/1.1" 200 OK
INFO: 127.0.0.1:37108 - "GET /api/v1/model-options/ltx2_22B_distilled_1_1 HTTP/1.1" 200 OK
INFO: 127.0.0.1:37108 - "POST /api/v1/upload HTTP/1.1" 200 OK
[Maestro] Installing download stall protection...
[Maestro] Importing WanGP engine...
[Maestro] WanGP loaded: 197 models available
[Workspace] Active workspace: default (outputs)
[Maestro] Gradio classic UI mounted at /classic
[Maestro] React UI serving from /home/professorjones/pinokio/api/Maestro.git/ui/dist
[Pipeline] Workspace=default, out_dir=outputs, wgp.save_path=outputs
INFO: 127.0.0.1:37108 - "POST /api/v1/director/pipeline/start HTTP/1.1" 200 OK
[LLM] Loading model: Abhiray/gemma-4-E4B-it-heretic-GGUF on cuda
[LLM] GGUF file already cached: /home/professorjones/pinokio/api/Maestro.git/app/services/../ckpts/llm/gemma-4-E4B-it-heretic/gemma-4-E4B-it-heretic-Q4_K_M.gguf
[LLM] GGUF file already cached: /home/professorjones/pinokio/api/Maestro.git/app/services/../ckpts/llm/gemma-4-E4B-it-heretic/mmproj-F16.gguf
[LLM] Vision support: mmproj loaded from Abhiray/gemma-4-E4B-it-heretic-GGUF
[LLM] Starting llama-server on port 42125
[Pipeline] Planning error: llama-server exited with code 127:
/home/professorjones/pinokio/api/Maestro.git/app/services/../ckpts/llm/bin/llama-server: error while loading shared libraries: libllama-common.so.0: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "/home/professorjones/pinokio/api/Maestro.git/app/services/director_pipeline.py", line 4844, in _run_pipeline
clip_plans, planned_clips = _run_planning(pid, params, pipeline_type)
File "/home/professorjones/pinokio/api/Maestro.git/app/services/director_pipeline.py", line 5452, in _run_planning
_ensure_llm_loaded(params)
File "/home/professorjones/pinokio/api/Maestro.git/app/services/director_pipeline.py", line 5415, in _ensure_llm_loaded
llm_service.load_model(model_id=desired_model, device=desired_device, provider=desired_provider, remote_url=desired_remote_url, api_key=desired_api_key)
File "/home/professorjones/pinokio/api/Maestro.git/app/services/llm_service.py", line 1553, in load_model
raise RuntimeError(f"llama-server exited with code {exit_code}:\n{output[-2000:]}")
RuntimeError: llama-server exited with code 127:
/home/professorjones/pinokio/api/Maestro.git/app/services/../ckpts/llm/bin/llama-server: error while loading shared libraries: libllama-common.so.0: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "/home/professorjones/pinokio/api/Maestro.git/app/services/director_pipeline.py", line 4844, in _run_pipeline
clip_plans, planned_clips = _run_planning(pid, params, pipeline_type)
File "/home/professorjones/pinokio/api/Maestro.git/app/services/director_pipeline.py", line 5452, in _run_planning
_ensure_llm_loaded(params)
File "/home/professorjones/pinokio/api/Maestro.git/app/services/director_pipeline.py", line 5415, in _ensure_llm_loaded
llm_service.load_model(model_id=desired_model, device=desired_device, provider=desired_provider, remote_url=desired_remote_url, api_key=desired_api_key)
File "/home/professorjones/pinokio/api/Maestro.git/app/services/llm_service.py", line 1553, in load_model
raise RuntimeError(f"llama-server exited with code {exit_code}:\n{output[-2000:]}")
RuntimeError: llama-server exited with code 127:
/home/professorjones/pinokio/api/Maestro.git/app/services/../ckpts/llm/bin/llama-server: error while loading shared libraries: libllama-common.so.0: cannot open shared object file: No such file or directory
Replies (0)
Up to 10 files, 25MB each. Images are optimized; GIFs -> MP4; videos 720p (max 120s).