0
Maestro AMD: ImportError: cannot import name 'group' from 'torch.distributed' (not limited to just maestro !)
myselft trying to figure it out...
Windows 11
RX 7900 XT
64gb ram (6000mhz)
I9 13900k
Pinokio 8.2.0
Maestro AMD 2.1.5
torch:
2.10.0a0+rocm7.10.0a20251120
vector-quantize-pytorch:
1.27.19
hasattr(torch.distributed, "group"):
False
Failure:
vector_quantize_pytorch.lookup_free_quantization.py
line:
from torch.distributed import nn as dist_nn
ImportError:
cannot import name 'group' from 'torch.distributed'
---------------------------------------------------pinokio log-----------------------------------------------------------
App: Maestro AMD (2Maestro-AMD.git)
Repo: https://github.com/yoyokits/Maestro-AMD.git
Generated: 2026-09-11T03:38:57.683Z
Pinokio: 8.2.0
Platform: win32 x64
Node: v22.21.1
Summary
System
{
"pinokio": {
"version": "8.2.0",
"node": "v22.21.1",
"platform": "win32",
"arch": "x64"
},
"hardware": {
"gpu": "amd",
"gpu_model": "amd radeon rx 7900 xt",
"ram_gb": 64,
"vram_gb": 20,
"gpu_driver": null,
"gpu_target": "gfx1100"
},
"os": {
"platform": "Windows",
"distro": "Microsoft Windows 11 Pro",
"release": "10.0.26200",
"codename": "25H2",
"kernel": "10.0.26200",
"arch": "x64",
"build": "26200",
"servicepack": "0.0",
"uefi": true
},
"system": {
"manufacturer": "Micro-Star International Co., Ltd.",
"model": "MS-7E06",
"version": "2.0",
"virtual": false
},
"cpu": {
"manufacturer": "Intel",
"brand": "Gen Intel® Core™ i9-13900K",
"vendor": "GenuineIntel",
"family": "6",
"model": "183",
"stepping": "1",
"speed": 3,
"speedMin": 3,
"speedMax": 3,
"cores": 32,
"physicalCores": 24,
"processors": 1,
"performanceCores": 32,
"efficiencyCores": 0,
"virtualization": true,
"cache": {
"l1d": 917504,
"l1i": 1310720,
"l2": 33554432,
"l3": 37748736
}
},
"memory": {
"total": 68418723840,
"free": 56876204032,
"used": 11542487040,
"active": 11542487040,
"available": 56876236800,
"buffers": 0,
"cached": 0,
"slab": 0,
"buffcache": 0,
"swaptotal": 40802189312,
"swapused": 0,
"swapfree": 40802189312
},
"gpus": [
{
"model": "intel(r) uhd graphics 770"
},
{
"model": "amd radeon rx 7900 xt"
}
],
"graphics": {
"controllers": [
{
"vendor": "Intel Corporation",
"model": "Intel(R) UHD Graphics 770",
"bus": "PCI",
"vram": 2047.99609375,
"vramDynamic": true
},
{
"vendor": "Advanced Micro Devices, Inc.",
"model": "AMD Radeon RX 7900 XT",
"bus": "PCI",
"vram": 20464,
"vramDynamic": true
}
],
"displays": [
{
"model": "SONY TV *30",
"main": true,
"builtin": false,
"connection": "HDMI",
"currentResX": 1280,
"currentResY": 720,
"resolutionX": 3840,
"resolutionY": 2160,
"pixelDepth": 32,
"currentRefreshRate": 60
}
]
},
"diagnostics": {
"platform": "win32",
"arch": "x64",
"running": {
"C:\\Users\\Pinokio\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\codex-auto\\pinokio.js?cwd=E:\\pinokio\\api\\2Maestro-AMD.git": true,
"E:\\pinokio\\api\\2Maestro-AMD.git\\start.js": true
},
"home": "E:\\pinokio",
"vars": {
"pip": {
"install": {
"torch": "pip3 install torch torchvision torchaudio"
}
}
},
"memory": {
"local": {
"E:\\pinokio\\api\\2Maestro-AMD.git\\start.js": {
"url": "http://127.0.0.1:42003"
}
},
"global": {},
"rpc": {
"E:\\pinokio\\api\\wan2gp-amd.git\\start.js": {
"method": "local.set",
"params": {
"url": "{{input.event[0]}}"
}
},
"E:\\pinokio\\api\\wan2gp-amd.git\\reset.js": {
"method": "fs.rm",
"params": {
"path": "app"
}
},
"E:\\pinokio\\api\\wan2gp-amd.git\\install.js": {
"method": "shell.run",
"params": {
"venv": "env",
"path": "app",
"message": [
"uv pip install -r requirements.txt --index-strategy unsafe-best-match",
"uv pip install hf-xet setuptools numpy==1.26.4"
]
}
},
"E:\\pinokio\\api\\wan2gp-amd.git\\torch.js": {
"when": "{{platform === 'win32' && gpu === 'amd' && /^gfx110[012]$/.test(gpu_target)}}",
"method": "shell.run",
"params": {
"bluefairy": "off",
"env": {
"UV_SKIP_WHEEL_FILENAME_CHECK": "1"
},
"venv_python": "{{args && args.venv_python ? args.venv_python : null}}",
"venv": "{{args && args.venv ? args.venv : null}}",
"path": "{{args && args.path ? args.path : '.'}}",
"message": "uv pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2-staging/gfx110X-all"
},
"next": null
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\install.js": {
"method": "input",
"params": {
"title": "Installation completed",
"description": "Click \"Start\" to get started. If anything looks wrong, run \"Diagnose\" from the menu."
}
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\torch.js": {
"method": "fs.write",
"params": {
"path": "Maestro/app/env-amd/.maestro_amd_v1.installed",
"text": "Maestro AMD ROCm runtime installed. Delete this file and run Update to reinstall it."
}
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\start.js": {
"method": "local.set",
"params": {
"url": "{{input.event[1]}}"
}
},
"C:\\Users\\Pinokio\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\codex-auto\\pinokio.js?cwd=E:\\pinokio\\api\\2Maestro-AMD.git": {
"when": "{{platform === 'win32'}}",
"id": "run",
"method": "shell.run",
"params": {
"shell": "{{kernel.path('bin/miniforge/Library/bin/bash.exe')}}",
"conda": {
"skip": true
},
"message": {
"_": [
"npx",
"-y",
"@openai/codex@latest",
"--yolo",
"-c",
"projects={ {{JSON.stringify(args.cwd)}}={trust_level=\"trusted\"} }",
"{{args.prompt || undefined}}"
]
},
"path": "{{args.cwd}}",
"input": true
},
"current": 0,
"total": 2
},
"C:\\Users\\Pinokio\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\codex-auto\\pinokio.js": {
"current": 0,
"total": 2
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\repair.js": {
"method": "input",
"params": {
"title": "Repair complete",
"description": "Your models and outputs were preserved. Click Start, or run Diagnose if problems persist."
}
}
},
"input": {
"E:\\pinokio\\api\\wan2gp-amd.git\\start.js": {
"id": "64e98af6-2a5e-4e19-b8e5-cd33f92b9bff",
"response": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\wan2gp-amd.git\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate E:\\pinokio\\api\\wan2gp-amd.git\\app\\env && python wgp.py\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\nDownloading ffmpeg-9.0.1-essentials_build.zip: 100%|███████████████████████████████████████████████████████████████████| 111M/111M [00:02<00:00, 49.4MB/s]\r\nLoaded plugin: Motion Designer (from motion_designer)\r\n* Running on local URL: http://localhost:7860",
"stdout": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\wan2gp-amd.git\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate E:\\pinokio\\api\\wan2gp-amd.git\\app\\env && python wgp.py\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\nDownloading ffmpeg-9.0.1-essentials_build.zip: 100%|███████████████████████████████████████████████████████████████████| 111M/111M [00:02<00:00, 49.4MB/s]\r\nLoaded plugin: Motion Designer (from motion_designer)\r\n* Running on local URL: http://localhost:7860",
"event": [
"http://localhost:7860"
]
},
"E:\\pinokio\\api\\wan2gp-amd.git\\reset.js": {},
"E:\\pinokio\\api\\wan2gp-amd.git\\install.js": {
"id": "c2ae6f26-9417-4fe9-953a-2e806f9e5290",
"response": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\wan2gp-amd.git\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & uv venv E:\\pinokio\\api\\wan2gp-amd.git\\app\\env --python 3.11 & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate E:\\pinokio\\api\\wan2gp-amd.git\\app\\env & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\deactivate & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate E:\\pinokio\\api\\wan2gp-amd.git\\app\\env && uv pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2-staging/gfx110X-all\r\nUsing CPython 3.11.15\r\nCreating virtual environment at: env\r\nActivate with: env\\Scripts\\activate\r\nUsing Python 3.11.15 environment at: env\r\nResolved 17 packages in 1.37s\r\nInstalled 17 packages in 12.57s\r\n + filelock==3.29.0\r\n + fsspec==2026.3.0\r\n + jinja2==3.1.6\r\n + markupsafe==3.0.3\r\n + mpmath==1.3.0\r\n + networkx==3.6.1\r\n + numpy==2.4.4\r\n + pillow==12.2.0\r\n + rocm==7.14.0a20260611\r\n + rocm-sdk-core==7.14.0a20260611\r\n + rocm-sdk-libraries-gfx110x-all==7.14.0a20260611\r\n + setuptools==80.9.0\r\n + sympy==1.14.0\r\n + torch==2.13.0a0+rocm7.14.0a20260611\r\n + torchaudio==2.11.0+rocm7.14.0a20260611\r\n + torchvision==0.28.0a0+rocm7.14.0a20260611\r\n + typing-extensions==4.15.0\r\n\r\n(env) (base) E:\\pinokio\\api\\wan2gp-amd.git\\app>",
"stdout": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\wan2gp-amd.git\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & uv venv E:\\pinokio\\api\\wan2gp-amd.git\\app\\env --python 3.11 & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate E:\\pinokio\\api\\wan2gp-amd.git\\app\\env & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\deactivate & E:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate E:\\pinokio\\api\\wan2gp-amd.git\\app\\env && uv pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2-staging/gfx110X-all\r\nUsing CPython 3.11.15\r\nCreating virtual environment at: env\r\nActivate with: env\\Scripts\\activate\r\nUsing Python 3.11.15 environment at: env\r\nResolved 17 packages in 1.37s\r\nInstalled 17 packages in 12.57s\r\n + filelock==3.29.0\r\n + fsspec==2026.3.0\r\n + jinja2==3.1.6\r\n + markupsafe==3.0.3\r\n + mpmath==1.3.0\r\n + networkx==3.6.1\r\n + numpy==2.4.4\r\n + pillow==12.2.0\r\n + rocm==7.14.0a20260611\r\n + rocm-sdk-core==7.14.0a20260611\r\n + rocm-sdk-libraries-gfx110x-all==7.14.0a20260611\r\n + setuptools==80.9.0\r\n + sympy==1.14.0\r\n + torch==2.13.0a0+rocm7.14.0a20260611\r\n + torchaudio==2.11.0+rocm7.14.0a20260611\r\n + torchvision==0.28.0a0+rocm7.14.0a20260611\r\n + typing-extensions==4.15.0\r\n\r\n(env) (base) E:\\pinokio\\api\\wan2gp-amd.git\\app>"
},
"E:\\pinokio\\api\\wan2gp-amd.git\\torch.js": null,
"E:\\pinokio\\api\\2Maestro-AMD.git\\install.js": {
"id": "a3d447d7-a574-47d8-8c06-f63da9ac1b42",
"response": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && python \"E:\\pinokio\\api\\2Maestro-AMD.git/update_state.py\" ui-done\r\n[update_state] UI build recorded at 11cd18e58d85\r\n\r\n(env-amd) (base) E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>",
"stdout": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && python \"E:\\pinokio\\api\\2Maestro-AMD.git/update_state.py\" ui-done\r\n[update_state] UI build recorded at 11cd18e58d85\r\n\r\n(env-amd) (base) E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>"
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\torch.js": {
"id": "931a1f2a-2a4e-42ea-94a6-64ff86324fa1",
"response": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && uv pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2-staging/gfx110X-dgpu --force-reinstall\r\nUsing Python 3.11.15 environment at: env-amd\r\nResolved 16 packages in 918ms\r\nPrepared 16 packages in 41ms\r\nInstalled 16 packages in 11.62s\r\n + filelock==3.29.0\r\n + fsspec==2026.3.0\r\n + jinja2==3.1.6\r\n + markupsafe==3.0.3\r\n + mpmath==1.3.0\r\n + networkx==3.6.1\r\n + numpy==2.3.1\r\n + pillow==12.2.0\r\n + rocm==7.10.0a20251120\r\n + rocm-sdk-core==7.10.0a20251120\r\n + rocm-sdk-libraries-gfx110x-dgpu==7.10.0a20251120\r\n + sympy==1.14.0\r\n + torch==2.10.0a0+rocm7.10.0a20251120\r\n + torchaudio==2.10.0a0+rocm7.10.0a20251120\r\n + torchvision==0.25.0a0+rocm7.10.0a20251120\r\n + typing-extensions==4.15.0\r\n\r\n(env-amd) (base) E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>",
"stdout": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && uv pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2-staging/gfx110X-dgpu --force-reinstall\r\nUsing Python 3.11.15 environment at: env-amd\r\nResolved 16 packages in 918ms\r\nPrepared 16 packages in 41ms\r\nInstalled 16 packages in 11.62s\r\n + filelock==3.29.0\r\n + fsspec==2026.3.0\r\n + jinja2==3.1.6\r\n + markupsafe==3.0.3\r\n + mpmath==1.3.0\r\n + networkx==3.6.1\r\n + numpy==2.3.1\r\n + pillow==12.2.0\r\n + rocm==7.10.0a20251120\r\n + rocm-sdk-core==7.10.0a20251120\r\n + rocm-sdk-libraries-gfx110x-dgpu==7.10.0a20251120\r\n + sympy==1.14.0\r\n + torch==2.10.0a0+rocm7.10.0a20251120\r\n + torchaudio==2.10.0a0+rocm7.10.0a20251120\r\n + torchvision==0.25.0a0+rocm7.10.0a20251120\r\n + typing-extensions==4.15.0\r\n\r\n(env-amd) (base) E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>"
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\start.js": {
"id": "aa0f2478-6fbe-4d8c-98b0-0bb2c44e088f",
"response": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && 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[Runtime] FlashAttention is unavailable (No module named 'flash_attn'); continuing with SageAttention/SDPA.\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\n[Runtime] Python 3.11.15 | PyTorch 2.10.0a0+rocm7.10.0a20251120 | CUDA none | AMD Radeon RX 7900 XT (sm_110)\r\n[Runtime] Kernels: Triton=missing, SageAttention=missing, Lightx2v NVFP4=missing, FlashAttention=missing, 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[Maestro] WanGP loaded: 203 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 E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\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": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && 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[Runtime] FlashAttention is unavailable (No module named 'flash_attn'); continuing with SageAttention/SDPA.\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\n[Runtime] Python 3.11.15 | PyTorch 2.10.0a0+rocm7.10.0a20251120 | CUDA none | AMD Radeon RX 7900 XT (sm_110)\r\n[Runtime] Kernels: Triton=missing, SageAttention=missing, Lightx2v NVFP4=missing, FlashAttention=missing, 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[Maestro] WanGP loaded: 203 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 E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\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"
]
},
"C:\\Users\\Pinokio\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\codex-auto\\pinokio.js?cwd=E:\\pinokio\\api\\2Maestro-AMD.git": {
"cwd": "E:\\pinokio\\api\\2Maestro-AMD.git",
"ask_ai": "1",
"prompt": "Investigate what went wrong. Inspect the app logs and explain the likely root cause and next fix."
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\repair.js": {
"id": "80343ef5-6923-410e-bf56-549b7372d3f0",
"response": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && python \"E:\\pinokio\\api\\2Maestro-AMD.git/update_state.py\" ui-done\r\n[update_state] UI build recorded at 11cd18e58d85\r\n\r\n(env-amd) (base) E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>",
"stdout": "Microsoft Windows [Version 10.0.26200.9445]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nE:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd\\Scripts\\activate E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app\\env-amd && python \"E:\\pinokio\\api\\2Maestro-AMD.git/update_state.py\" ui-done\r\n[update_state] UI build recorded at 11cd18e58d85\r\n\r\n(env-amd) (base) E:\\pinokio\\api\\2Maestro-AMD.git\\Maestro\\app>"
}
},
"args": {
"E:\\pinokio\\api\\wan2gp-amd.git\\start.js": {},
"E:\\pinokio\\api\\wan2gp-amd.git\\reset.js": {},
"E:\\pinokio\\api\\wan2gp-amd.git\\install.js": {},
"E:\\pinokio\\api\\wan2gp-amd.git\\torch.js": {
"venv_python": "3.11",
"venv": "env",
"path": "app"
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\install.js": {},
"E:\\pinokio\\api\\2Maestro-AMD.git\\torch.js": {
"venv": "env-amd",
"venv_python": "3.11",
"path": "Maestro/app"
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\start.js": {},
"C:\\Users\\Pinokio\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\codex-auto\\pinokio.js?cwd=E:\\pinokio\\api\\2Maestro-AMD.git": {
"cwd": "E:\\pinokio\\api\\2Maestro-AMD.git",
"ask_ai": "1",
"prompt": "Investigate what went wrong. Inspect the app logs and explain the likely root cause and next fix."
},
"E:\\pinokio\\api\\2Maestro-AMD.git\\repair.js": {}
}
},
"procs": {},
"gpu": "amd",
"gpus": [
{
"name": "intel corporation",
"model": "intel(r) uhd graphics 770",
"driver": null
},
{
"name": "advanced micro devices, inc.",
"model": "amd radeon rx 7900 xt",
"driver": null
}
],
"gpu_model": "amd radeon rx 7900 xt",
"gpu_driver": null,
"gpu_target": "gfx1100",
"ram": 64,
"vram": 20,
"version": "8.2.0",
"graphics": {
"controllers": [
{
"vendor": "Intel Corporation",
"model": "Intel(R) UHD Graphics 770",
"bus": "PCI",
"vram": 2047.99609375,
"vramDynamic": true,
"subDeviceId": "7E061462"
},
{
"vendor": "Advanced Micro Devices, Inc.",
"model": "AMD Radeon RX 7900 XT",
"bus": "PCI",
"vram": 20464,
"vramDynamic": true,
"subDeviceId": "10021002"
}
],
"displays": [
{
"vendor": "SNY",
"model": "SONY TV *30",
"serial": "16843009",
"productionYear": 2020,
"displayId": "display\\sny7905\\7&267d8685&0&uid524_0",
"deviceName": "\\\\.\\DISPLAY1",
"main": true,
"builtin": false,
"connection": "HDMI",
"resolutionX": 3840,
"resolutionY": 2160,
"sizeX": 166,
"sizeY": 93,
"pixelDepth": 32,
"currentResX": 1280,
"currentResY": 720,
"positionX": 0,
"positionY": 0,
"currentRefreshRate": 60
}
]
},
"audio": [
{
"id": "HDAUDIO\\FUNC_01&VEN_1002&DEV_AA01&SUBSYS_00AA0100&REV_1008\\7&2D3E209E&0&0001",
"name": "AMD High Definition Audio Device",
"manufacturer": "Advanced Micro Devices",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "Sound Driver",
"in": null,
"out": null,
"status": "enabled"
},
{
"id": "ROOT\\AMDSAFD&FUN_01&REV_01\\0000",
"name": "AMD Streaming Audio Device",
"manufacturer": "AMD",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "",
"in": null,
"out": null,
"status": "enabled"
},
{
"id": "ROOT\\STEAMSTREAMINGSPEAKERS\\0000",
"name": "Steam Streaming Speakers",
"manufacturer": "Valve Corporation Audio DDK",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "Speaker",
"in": null,
"out": null,
"status": "enabled"
},
{
"id": "HDAUDIO\\FUNC_01&VEN_10EC&DEV_0897&SUBSYS_14629E06&REV_1004\\4&39B4B8A8&0&0001",
"name": "Realtek High Definition Audio",
"manufacturer": "Realtek",
"revision": null,
"driver": null,
"default": null,
"channel": null,
"type": "Sound Driver",
"in": null,
"out": null,
"status": "enabled"
}
],
"mem": {
"total": 68418723840,
"free": 56876204032,
"used": 11542487040,
"active": 11542487040,
"available": 56876236800,
"buffers": 0,
"cached": 0,
"slab": 0,
"buffcache": 0,
"reclaimable": 0,
"swaptotal": 40802189312,
"swapused": 0,
"swapfree": 40802189312,
"writeback": null,
"dirty": null
},
"osInfo": {
"platform": "Windows",
"distro": "Microsoft Windows 11 Pro",
"release": "10.0.26200",
"codename": "25H2",
"kernel": "10.0.26200",
"arch": "x64",
"hostname": "MSI-BEAST",
"fqdn": "MSI-BEAST",
"codepage": "437",
"logofile": "windows",
"serial": "00330-81624-19097-AA421",
"build": "26200",
"servicepack": "0.0",
"uefi": true,
"hypervisor": true,
"remoteSession": false
},
"shell": "CMD",
"system": {
"manufacturer": "Micro-Star International Co., Ltd.",
"model": "MS-7E06",
"version": "2.0",
"serial": "Default string",
"uuid": "f8923035-6c8a-6d1e-a71e-d843ae5d8366",
"sku": "Default string",
"virtual": false
},
"cpu": {
"manufacturer": "Intel",
"brand": "Gen Intel® Core™ i9-13900K",
"vendor": "GenuineIntel",
"family": "6",
"model": "183",
"stepping": "1",
"revision": "",
"voltage": "",
"speed": 3,
"speedMin": 3,
"speedMax": 3,
"governor": "",
"cores": 32,
"physicalCores": 24,
"performanceCores": 32,
"efficiencyCores": 0,
"processors": 1,
"socket": "LGA1700",
"flags": "de pse mce sep mtrr mca cmov psn clfsh ds mmx fxsr sse sse2 ss htt tm ia64 pbe",
"virtualization": true,
"cache": {
"l1d": 917504,
"l1i": 1310720,
"l2": 33554432,
"l3": 37748736
}
}
}
}
Logs
logs/api/start.js/1789097085729
Source: api / start.js
Lines: 10 total, last 10 included
[memory]
{"ts":1789097091382,"step":2,"input":{"id":"a59892a5-da9c-4301-bd28-2ec59652603d"},"args":{},"global":{},"local":{},"port":42003}
[memory]
Microsoft Windows [Version 10.0.26200.9445]
(c) Microsoft Corporation. All rights reserved.
E:\pinokio\api\2Maestro-AMD.git\Maestro\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Scripts\activate E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd && python "E:\pinokio\api\2Maestro-AMD.git/verify_rocm_torch.py" --preflight
(env-amd) (base) E:\pinokio\api\2Maestro-AMD.git\Maestro\app>
logs/api/start.js/1789097091394
Source: api / start.js
Lines: 8 total, last 8 included
[api shell.run]
Microsoft Windows [Version 10.0.26200.9445]
(c) Microsoft Corporation. All rights reserved.
E:\pinokio\api\2Maestro-AMD.git\Maestro\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Scripts\activate E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd && python "E:\pinokio\api\2Maestro-AMD.git/configure_amd_defaults.py"
[amd_defaults] AMD defaults already in place
(env-amd) (base) E:\pinokio\api\2Maestro-AMD.git\Maestro\app>
logs/api/start.js/1789097097032
Source: api / start.js
Lines: 121 total, last 121 included
[api shell.run]
Microsoft Windows [Version 10.0.26200.9445]
(c) Microsoft Corporation. All rights reserved.
E:\pinokio\api\2Maestro-AMD.git\Maestro\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Scripts\activate E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd && python launch.py
[Maestro] Installing download stall protection...
[safe_download] tqdm download hook installed
[Maestro] Importing WanGP engine...
[Runtime] FlashAttention is unavailable (No module named 'flash_attn'); continuing with SageAttention/SDPA.
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
[Runtime] Python 3.11.15 | PyTorch 2.10.0a0+rocm7.10.0a20251120 | CUDA none | AMD Radeon RX 7900 XT (sm_110)
[Runtime] Kernels: Triton=missing, SageAttention=missing, Lightx2v NVFP4=missing, FlashAttention=missing, 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
[Maestro] WanGP loaded: 203 models available
[Workspace] Active workspace: default (outputs)
[Maestro] Gradio classic UI mounted at /classic
[Maestro] React UI serving from E:\pinokio\api\2Maestro-AMD.git\Maestro\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 [10608]
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: 127.0.0.1:52625 - "POST /api/v1/generate HTTP/1.1" 200 OK
[VRAM] Job 4cb6a524: coefficient 0.80 → 0.700 (cap 16.0GB → 14.0GB)
[VRAM] -0.100 for 1 extra pipeline stage(s) (2.0 GB)
[load] Task 1/1 ready, ID: 1, model: ace_step_v1_5_turbo_lm_4b
[Gen 4cb6a524] save_path locked to: outputs
[Task 1/1] [Intro]
(Piano arpeggio swells)
Holdin' onto the light
Throu...
pose/dw-ll_ucoco_384.onnx: 100%|████████████████████████████████████████████████████████████████████████████████| 134M/134M [00:03<00:00, 34.2MB/s]
pose/yolox_l.onnx: 100%|████████████████████████████████████████████████████████████████████████████████████████| 217M/217M [00:06<00:00, 35.9MB/s]
scribble/netG_A_latest.pth: 100%|█████████████████████████████████████████████████████████████████████████████| 17.2M/17.2M [00:01<00:00, 10.4MB/s]
flow/raft-things.pth: 100%|███████████████████████████████████████████████████████████████████████████████████| 21.1M/21.1M [00:01<00:00, 15.8MB/s]
depth/depth_anything_v2_vitl.pth: 100%|███████████████████████████████████████████████████████████████████████| 1.34G/1.34G [00:24<00:00, 55.2MB/s]
depth/depth_anything_v2_vitb.pth: 100%|█████████████████████████████████████████████████████████████████████████| 390M/390M [00:08<00:00, 43.8MB/s]
config.json: 1.60kB [00:00, ?B/s]
feature_extractor_config.json: 1.60kB [00:00, 3.78MB/s]
wav2vec/model.safetensors: 100%|████████████████████████████████████████████████████████████████████████████████| 378M/378M [00:06<00:00, 59.2MB/s]
preprocessor_config.json: 100%|████████████████████████████████████████████████████████████████████████████████████| 159/159 [00:00<00:00, 420kB/s]
special_tokens_map.json: 100%|██████████████████████████████████████████████████████████████████████████████████| 85.0/85.0 [00:00<00:00, 56.3kB/s]
tokenizer_config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 163/163 [00:00<?, ?B/s]
vocab.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 291/291 [00:00<?, ?B/s]
config.json: 1.95kB [00:00, 1.10MB/s]
chinese-wav2vec2-base/pytorch_model.bin: 100%|██████████████████████████████████████████████████████████████████| 380M/380M [00:06<00:00, 62.4MB/s]
preprocessor_config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████| 160/160 [00:00<?, ?B/s]
roformer/model_bs_roformer_ep_317_sdr_12(…): 100%|██████████████████████████████████████████████████████████████| 639M/639M [00:08<00:00, 74.5MB/s]
(…)odel_bs_roformer_ep_317_sdr_12.9755.yaml: 2.27kB [00:00, ?B/s]
download_checks.json: 28.3kB [00:00, ?B/s]
pyannote/pyannote_model_wespeaker-voxcel(…): 100%|████████████████████████████████████████████████████████████| 26.6M/26.6M [00:01<00:00, 20.2MB/s]
pyannote/pytorch_model_segmentation-3.0.(…): 100%|████████████████████████████████████████████████████████████| 5.91M/5.91M [00:00<00:00, 17.5MB/s]
det_align/detface.pt: 100%|█████████████████████████████████████████████████████████████████████████████████████| 187M/187M [00:04<00:00, 40.3MB/s]
rife4.26.pkl: 100%|███████████████████████████████████████████████████████████████████████████████████████████| 24.6M/24.6M [00:00<00:00, 26.3MB/s]
mask/sam_vit_h_4b8939_fp16.safetensors: 100%|█████████████████████████████████████████████████████████████████| 1.28G/1.28G [00:23<00:00, 54.2MB/s]
mask/matanyone.safetensors: 100%|███████████████████████████████████████████████████████████████████████████████| 141M/141M [00:04<00:00, 32.7MB/s]
config.json: 2.90kB [00:00, ?B/s]
ace_step_v1_5_transformer_quanto_bf16_in(…): 100%|████████████████████████████████████████████████████████████| 2.40G/2.40G [00:42<00:00, 56.0MB/s]
ace_step15/ace_step_v1_5_audio_vae_bf16.(…): 100%|██████████████████████████████████████████████████████████████| 337M/337M [00:06<00:00, 48.8MB/s]
ace_step15/silence_latent.pt: 100%|███████████████████████████████████████████████████████████████████████████| 3.84M/3.84M [00:00<00:00, 14.9MB/s]
Qwen3-Embedding-0.6B/model.safetensors: 100%|█████████████████████████████████████████████████████████████████| 1.19G/1.19G [00:19<00:00, 60.9MB/s]
config.json: 1.36kB [00:00, ?B/s]
Qwen3-Embedding-0.6B/tokenizer.json: 100%|████████████████████████████████████████████████████████████████████| 11.4M/11.4M [00:02<00:00, 4.21MB/s]
tokenizer_config.json: 5.40kB [00:00, ?B/s]
special_tokens_map.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 613/613 [00:00<?, ?B/s]
config.json: 1.56kB [00:00, ?B/s]
acestep-5Hz-lm-4B/tokenizer.json: 100%|███████████████████████████████████████████████████████████████████████| 24.3M/24.3M [00:03<00:00, 8.05MB/s]
acestep-5Hz-lm-4B/tokenizer_config.json: 100%|████████████████████████████████████████████████████████████████| 14.1M/14.1M [00:00<00:00, 16.6MB/s]
special_tokens_map.json: 1.82MB [00:00, 29.8MB/s]
added_tokens.json: 2.22MB [00:00, 94.9MB/s]
merges.txt: 1.67MB [00:00, 38.3MB/s]
vocab.json: 2.78MB [00:00, 89.6MB/s]
chat_template.jinja: 4.17kB [00:00, ?B/s]
Loading Model 'ckpts\ace_step_v1_5_transformer_quanto_bf16_int8.safetensors' ...
acestep-5Hz-lm-4B/acestep-5Hz-lm-4B_quan(…): 100%|████████████████████████████████████████████████████████████| 4.75G/4.75G [01:16<00:00, 62.0MB/s]
Loading Text Encoder 'ckpts\acestep-5Hz-lm-4B\acestep-5Hz-lm-4B_quanto_bf16_int8.safetensors' ...
[ERROR] cannot import name 'group' from 'torch.distributed' (E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\torch\distributed\__init__.py)
Traceback (most recent call last):
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\launch.py", line 25548, in error_handler
wgp.generate_video(task, send_cmd, plugin_data=plugin_data, **filtered_params)
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\services\generation_memory.py", line 68, in wrapped
result = function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\wgp.py", line 7749, in generate_video
wan_model, offloadobj = load_models(
^^^^^^^^^^^^
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\wgp.py", line 4474, in load_models
wan_model, pipe = model_type_handler.load_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\models\TTS\ace_step_handler.py", line 525, in load_model
from .ace_step15.pipeline_ace_step15 import ACEStep15Pipeline
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\models\TTS\ace_step15\pipeline_ace_step15.py", line 23, in <module>
from .models.ace_step15_hf import AceStepConditionGenerationModel
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\models\TTS\ace_step15\models\ace_step15_hf.py", line 4, in <module>
from .modeling_acestep_v15_turbo import AceStepConditionGenerationModel as _AceStepHFModel
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\models\TTS\ace_step15\models\modeling_acestep_v15_turbo.py", line 41, in <module>
from vector_quantize_pytorch import ResidualFSQ
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\vector_quantize_pytorch\__init__.py", line 5, in <module>
from vector_quantize_pytorch.lookup_free_quantization import LFQ
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\vector_quantize_pytorch\lookup_free_quantization.py", line 15, in <module>
from torch.distributed import nn as dist_nn
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\torch\distributed\nn\__init__.py", line 3, in <module>
from .functional import * # noqa: F403
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\torch\distributed\nn\functional.py", line 9, in <module>
from torch.distributed import group, ReduceOp
ImportError: cannot import name 'group' from 'torch.distributed' (E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\torch\distributed\__init__.py)
[ERROR] cannot import name 'group' from 'torch.distributed' (E:\pinokio\api\2Maestro-AMD.git\Maestro\app\env-amd\Lib\site-packages\torch\distributed\__init__.py)
==================================================
Queue completed: 0/1 tasks in 4m 24s
Replies (0)
Up to 10 files, 25MB each. Images are optimized; GIFs -> MP4; videos 720p (max 120s).