0
Wan2GP crashes after phase 22, 49% shows model loaded and starts using ram 32gb instead of vram from my amd 7900 xtx 24gb
App: Wan2GP - AMD (wan2gp-amd.git)
Repo: https://github.com/6Morpheus6/wan2gp-amd.git
Generated: 2026-09-15T18:50:05.047Z
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 xtx",
"ram_gb": 31,
"vram_gb": 24,
"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": "Gigabyte Technology Co., Ltd.",
"model": "B850 GAMING X WIFI6E",
"version": "Default string-WCP-ADO",
"virtual": false
},
"cpu": {
"manufacturer": "AMD",
"brand": "Ryzen 7 9800X3D 8-Core Processor",
"vendor": "AuthenticAMD",
"family": "26",
"model": "68",
"stepping": "0",
"revision": "17408",
"speed": 4.7,
"speedMin": 4.7,
"speedMax": 4.7,
"cores": 16,
"physicalCores": 8,
"processors": 1,
"performanceCores": 16,
"efficiencyCores": 0,
"virtualization": true,
"cache": {
"l1d": 320,
"l1i": 320,
"l2": 8388608,
"l3": 100663296
}
},
"memory": {
"total": 33407348736,
"free": 26165575680,
"used": 7241773056,
"active": 7241773056,
"available": 26165575680,
"buffers": 0,
"cached": 0,
"slab": 0,
"buffcache": 0,
"swaptotal": 5368709120,
"swapused": 0,
"swapfree": 5368709120
},
"gpus": [
{
"model": "amd radeon(tm) graphics"
},
{
"model": "amd radeon rx 7900 xtx"
}
],
"graphics": {
"controllers": [
{
"vendor": "Advanced Micro Devices, Inc.",
"model": "AMD Radeon(TM) Graphics",
"bus": "PCI",
"vram": 512,
"vramDynamic": true
},
{
"vendor": "Advanced Micro Devices, Inc.",
"model": "AMD Radeon RX 7900 XTX",
"bus": "PCI",
"vram": 24560,
"vramDynamic": true
}
],
"displays": [
{
"model": "LG ULL HD",
"main": true,
"builtin": false,
"connection": "HDMI",
"currentResX": 1920,
"currentResY": 1080,
"resolutionX": 1920,
"resolutionY": 1080,
"pixelDepth": 32,
"currentRefreshRate": 60
}
]
},
"diagnostics": {
"platform": "win32",
"arch": "x64",
"running": {
"C:\\pinokio\\api\\wan2gp-amd.git\\start.js": true,
"C:\\Users\\GAGAN\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\claude-auto\\pinokio.js?cwd=C:\\pinokio\\api\\wan2gp-amd.git": true
},
"home": "C:\\pinokio",
"vars": {
"pip": {
"install": {
"torch": "pip3 install torch torchvision torchaudio"
}
}
},
"memory": {
"local": {
"C:\\pinokio\\api\\wan2gp-amd.git\\start.js": {
"url": "http://localhost:7860/deepy/"
}
},
"global": {},
"rpc": {
"C:\\pinokio\\api\\wan2gp-amd.git\\start.js": {
"method": "local.set",
"params": {
"url": "{{input.event[0]}}"
}
},
"C:\\Users\\GAGAN\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\claude-auto\\pinokio.js?cwd=C:\\pinokio\\api\\wan2gp-amd.git": {
"when": "{{platform === 'win32'}}",
"id": "run",
"method": "shell.run",
"params": {
"shell": "{{kernel.path('bin/miniforge/Library/bin/bash.exe')}}",
"conda": {
"skip": true
},
"env": {
"CLAUDE_CODE_GIT_BASH_PATH": "{{kernel.path('bin/miniforge/Library/bin/bash.exe')}}",
"CLAUBBIT": "true"
},
"message": {
"_": [
"npx",
"-y",
"@anthropic-ai/claude-code@latest",
"--settings",
"{\"skipDangerousModePermissionPrompt\":true}",
"--dangerously-skip-permissions",
"{{args.prompt || undefined}}"
]
},
"path": "{{args.cwd}}",
"input": true,
"buffer": 1024
},
"current": 0,
"total": 2
},
"C:\\Users\\GAGAN\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\claude-auto\\pinokio.js": {
"current": 0,
"total": 2
}
},
"input": {
"C:\\pinokio\\api\\wan2gp-amd.git\\start.js": {
"id": "de7dc07f-440d-437f-b17f-848d5f7bf8f6",
"response": "Microsoft Windows [Version 10.0.26200.9457]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nC:\\pinokio\\api\\wan2gp-amd.git\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate C:\\pinokio\\api\\wan2gp-amd.git\\app\\env & bluefairy-activate.cmd && python wgp.py\r\n[OK] bluefairy active: uv/npm/bun protection enabled\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\nLoaded plugin: Motion Designer (from motion_designer)\r\nWanGP web authentication disabled.\r\nDeepy Web app: http://localhost:7860/deepy/",
"stdout": "Microsoft Windows [Version 10.0.26200.9457]\r\n(c) Microsoft Corporation. All rights reserved.\r\n\r\nC:\\pinokio\\api\\wan2gp-amd.git\\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\\pinokio\\api\\wan2gp-amd.git\\app\\env\\Scripts\\activate C:\\pinokio\\api\\wan2gp-amd.git\\app\\env & bluefairy-activate.cmd && python wgp.py\r\n[OK] bluefairy active: uv/npm/bun protection enabled\r\n[GGUF][llama.cpp CUDA] kernels unavailable, using fallback\r\nLoaded plugin: Motion Designer (from motion_designer)\r\nWanGP web authentication disabled.\r\nDeepy Web app: http://localhost:7860/deepy/",
"event": [
"http://localhost:7860/deepy/"
]
},
"C:\\Users\\GAGAN\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\claude-auto\\pinokio.js?cwd=C:\\pinokio\\api\\wan2gp-amd.git": {
"cwd": "C:\\pinokio\\api\\wan2gp-amd.git",
"ask_ai": "1",
"prompt": "Investigate what went wrong. Inspect the app logs and explain the likely root cause and next fix."
}
},
"args": {
"C:\\pinokio\\api\\wan2gp-amd.git\\start.js": {},
"C:\\Users\\GAGAN\\AppData\\Local\\Programs\\Pinokio\\resources\\app.asar\\node_modules\\pinokiod\\system\\plugin\\claude-auto\\pinokio.js?cwd=C:\\pinokio\\api\\wan2gp-amd.git": {
"cwd": "C:\\pinokio\\api\\wan2gp-amd.git",
"ask_ai": "1",
"prompt": "Investigate what went wrong. Inspect the app logs and explain the likely root cause and next fix."
}
}
},
"procs": {},
"gpu": "amd",
"gpus": [
{
"name": "advanced micro devices, inc.",
"model": "amd radeon(tm) graphics",
"driver": null
},
{
"name": "advanced micro devices, inc.",
"model": "amd radeon rx 7900 xtx",
"driver": null
}
],
"gpu_model": "amd radeon rx 7900 xtx",
"gpu_driver": null,
"gpu_target": "gfx1100",
"ram": 31,
"vram": 24,
"version": "8.2.0",
"osInfo": {
"platform": "Windows",
"distro": "Microsoft Windows 11 Pro",
"release": "10.0.26200",
"codename": "25H2",
"kernel": "10.0.26200",
"arch": "x64",
"hostname": "DESKTOP-IE6QRK3",
"fqdn": "DESKTOP-IE6QRK3",
"codepage": "437",
"logofile": "windows",
"serial": "00330-81624-19282-AA060",
"build": "26200",
"servicepack": "0.0",
"uefi": true,
"hypervisor": true,
"remoteSession": false
},
"graphics": {
"controllers": [
{
"vendor": "Advanced Micro Devices, Inc.",
"model": "AMD Radeon(TM) Graphics",
"bus": "PCI",
"vram": 512,
"vramDynamic": true,
"subDeviceId": "D0001458"
},
{
"vendor": "Advanced Micro Devices, Inc.",
"model": "AMD Radeon RX 7900 XTX",
"bus": "PCI",
"vram": 24560,
"vramDynamic": true,
"subDeviceId": "0E3B1002"
}
],
"displays": [
{
"vendor": "GSM",
"model": "LG ULL HD",
"serial": "16843009",
"productionYear": 2016,
"displayId": "display\\gsm5b55\\7&af7aceb&0&uid780_0",
"deviceName": "\\\\.\\DISPLAY1",
"main": true,
"builtin": false,
"connection": "HDMI",
"resolutionX": 1920,
"resolutionY": 1080,
"sizeX": 48,
"sizeY": 27,
"pixelDepth": 32,
"currentResX": 1920,
"currentResY": 1080,
"positionX": 0,
"positionY": 0,
"currentRefreshRate": 60
}
]
},
"audio": [
{
"id": "HDAUDIO\\FUNC_01&VEN_10EC&DEV_0897&SUBSYS_1458A194&REV_1005\\5&22057C6F&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"
},
{
"id": "HDAUDIO\\FUNC_01&VEN_1002&DEV_AA01&SUBSYS_00AA0100&REV_1008\\7&1F8A3C4&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": "HDAUDIO\\FUNC_01&VEN_1002&DEV_AA01&SUBSYS_00AA0100&REV_1008\\5&28A47E64&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"
}
],
"mem": {
"total": 33407348736,
"free": 26165575680,
"used": 7241773056,
"active": 7241773056,
"available": 26165575680,
"buffers": 0,
"cached": 0,
"slab": 0,
"buffcache": 0,
"reclaimable": 0,
"swaptotal": 5368709120,
"swapused": 0,
"swapfree": 5368709120,
"writeback": null,
"dirty": null
},
"shell": "CMD",
"system": {
"manufacturer": "Gigabyte Technology Co., Ltd.",
"model": "B850 GAMING X WIFI6E",
"version": "Default string-WCP-ADO",
"serial": "Default string",
"uuid": "03560230-040f-05a2-8806-0d0700080009",
"sku": "Default string",
"virtual": false
},
"cpu": {
"manufacturer": "AMD",
"brand": "Ryzen 7 9800X3D 8-Core Processor",
"vendor": "AuthenticAMD",
"family": "26",
"model": "68",
"stepping": "0",
"revision": "17408",
"voltage": "",
"speed": 4.7,
"speedMin": 4.7,
"speedMax": 4.7,
"governor": "",
"cores": 16,
"physicalCores": 8,
"performanceCores": 16,
"efficiencyCores": 0,
"processors": 1,
"socket": "AM5",
"flags": "de pse tsc sep mtrr mca cmov psn clfsh ds mmx fxsr sse sse2 ss htt tm ia64 pbe",
"virtualization": true,
"cache": {
"l1d": 320,
"l1i": 320,
"l2": 8388608,
"l3": 100663296
}
}
}
}
Logs
logs/api/start.js/1789494615807
Source: api / start.js
Lines: 41 total, last 41 included
[api shell.run]
Microsoft Windows [Version 10.0.26200.9457]
(c) Microsoft Corporation. All rights reserved.
C:\pinokio\api\wan2gp-amd.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\wan2gp-amd.git\app\env\Scripts\activate C:\pinokio\api\wan2gp-amd.git\app\env & bluefairy-activate.cmd && python wgp.py
[OK] bluefairy active: uv/npm/bun protection enabled
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
Loaded plugin: Motion Designer (from motion_designer)
WanGP web authentication disabled.
Deepy Web app: http://localhost:7860/deepy/
* Running on local URL: http://localhost:7860
* To create a public link, set `share=True` in `launch()`.
[Prompt Enhancer / Deepy] Speculative Decoding disabled automatically because the selected model does not support it.
[Prompt Enhancer / Deepy] Fast KV Cache quantization disabled automatically because GGUF kernels do not meet the 1.0.13+ requirement.
[Qwen3.5VL][Qwen3.5-4B Abliterated][quanto_int8] Loading text checkpoint: .\ckpts\Qwen3_5_4B_Abliterated\Qwen3.5-4B-Abliterated_quanto_bf16_int8.safetensors
[Qwen3.5VL][Qwen3.5-4B Abliterated] Text generation engine: cg
************ Memory Management for the GPU Poor (mmgp 3.8.0) by DeepBeepMeep ************
Hooked to model 'prompt_enhancer_image_caption_vision_tower_model' (Qwen3_5VisionModel)
Hooked to model 'prompt_enhancer_image_caption_embedding_model' (Embedding)
Hooked to model 'prompt_enhancer_llm_model' (Qwen3_5ForCausalLM)
[AssistantRuntime] Deepy action maximum: thought=4,096, statement=4,096, tool=4,096 tokens (context_window=16,386).
Loading Model 'ckpts\ltx-2.5-22b-distilled_diffusion_model_int8_convrot.safetensors' ...
Loading Text Encoder 'ckpts\gemma4-12b-ltx-v1\gemma4-12b-ltx-v1_int8_convrot.safetensors' ...
Switching to partial pinning since full requirements for pinned models is 18561.5 MB while estimated available reservable RAM is 12743.9 MB. You may increase the value of parameter 'perc_reserved_mem_max' to a value higher than 0.40 to force full pinnning.
Partial pinning of data of 'transformer' to reserved RAM
The model was partially pinned to reserved RAM: 58 large blocks spread across 12634.72 MB
Hooked to model 'transformer' (X0Model)
Async loading plan for model 'transformer' : base size of 643.23 MB will be preloaded with a 369.71 MB async circular shuttle
Hooked to model 'text_encoder' (Gemma4UnifiedForCausalLM)
Async loading plan for model 'text_encoder' : base size of 1920.01 MB will be preloaded with a 230.75 MB async circular shuttle
Hooked to model 'text_embedding_projection' (GemmaFeaturesExtractorProjLinear)
Hooked to model 'vae' (VideoDecoder)
Hooked to model 'video_encoder' (VideoEncoder)
Hooked to model 'audio_encoder' (AudioEncoder)
Hooked to model 'audio_decoder' (AudioDecoder)
Hooked to model 'vocoder' (VocoderWithBWE)
Hooked to model 'spatial_upsampler' (LatentUpsampler)
Hooked to model 'video_embeddings_connector' (Embeddings1DConnector)
Hooked to model 'audio_embeddings_connector' (Embeddings1DConnector)
(env) (base) C:\pinokio\api\wan2gp-amd.git\app>
Replies (1)
Up to 10 files, 25MB each. Images are optimized; GIFs -> MP4; videos 720p (max 120s).