[00:00] Crash dump logging enabled: D:\a\comfy-gpu-ci\comfy-gpu-ci\comfy-test-logs\GaussianPack-1923\dev\windows-cpu\crash_dump.log [00:00] [00:00] [1/5] SYNTAX [00:00] ---------------------------------------- [00:00] [DEBUG] server=None, api=None [00:00] Found pyproject.toml (modern format) [00:00] Found requirements.txt (legacy format) [00:00] Unicode check: OK (all characters cp1252-safe) [00:00] Forbidden patterns check: OK [00:00] [SYNTAX] PASSED [00:00] [00:00] [2/5] INSTALL [00:00] ---------------------------------------- [00:00] [DEBUG] server=None, api=None [00:00] Setting up ComfyUI... [00:00] Creating virtual environment at D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv... [00:00] Running: uv venv D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv --python 3.12 [00:01] torch_version='2.10.0' -> pinning torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 [00:01] Cloning ComfyUI (latest) to D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI... [00:01] Running: git clone --depth 1 https://github.com/comfyanonymous/ComfyUI.git D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI [00:03] Pinning torch family from https://download.pytorch.org/whl/cpu: torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 [00:03] Running: uv pip install --python D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv\Scripts\python.exe --index-url https://download.pytorch.org/whl/cpu --extra-index-url https://pypi.org/simple --index-strategy unsafe-best-match torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 [00:28] Installing ComfyUI requirements into D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv... [00:28] comfyui-frontend-package==1.44.19 [00:28] comfyui-workflow-templates==0.9.82 [00:28] comfyui-embedded-docs==0.5.1 [00:28] torch [00:28] torchsde [00:28] torchvision [00:28] torchaudio [00:28] numpy>=1.25.0 [00:28] einops [00:28] transformers>=4.50.3 [00:28] tokenizers>=0.13.3 [00:28] sentencepiece [00:28] safetensors>=0.4.2 [00:28] aiohttp>=3.11.8 [00:28] yarl>=1.18.0 [00:28] pyyaml [00:28] Pillow [00:28] scipy [00:28] tqdm [00:28] psutil [00:28] alembic [00:28] SQLAlchemy>=2.0.0 [00:28] filelock [00:28] av>=14.2.0 [00:28] comfy-kitchen>=0.2.8 [00:28] comfy-aimdo==0.4.5 [00:28] requests [00:28] simpleeval>=1.0.0 [00:28] blake3 [00:28] [00:28] #non essential dependencies: [00:28] kornia>=0.7.1 [00:28] spandrel [00:28] pydantic~=2.0 [00:28] pydantic-settings~=2.0 [00:28] PyOpenGL [00:28] glfw [00:28] Running: uv pip install --python D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv\Scripts\python.exe --index-url https://download.pytorch.org/whl/cpu --extra-index-url https://pypi.org/simple --index-strategy unsafe-best-match -r D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\requirements.txt [00:55] Installing custom node... [00:55] Copying ComfyUI-GaussianPack to D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\ComfyUI-GaussianPack... [00:55] Installing node requirements... [00:55] plyfile [00:55] git+https://github.com/saliteta/NanoGS.git [00:55] Running: uv pip install --python D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv\Scripts\python.exe --index-url https://download.pytorch.org/whl/cpu --extra-index-url https://pypi.org/simple --index-strategy unsafe-best-match -r D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\ComfyUI-GaussianPack\requirements.txt [01:06] Installing validation endpoint... [01:06] Cloning PozzettiAndrea/ComfyUI-validate-endpoint... [01:06] Running: git clone --depth 1 https://x-access-token:***@github.com/PozzettiAndrea/ComfyUI-validate-endpoint.git D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\ComfyUI-validate-endpoint [01:06] [INSTALL] PASSED [01:06] [01:06] [3/5] REGISTRATION [01:06] ---------------------------------------- [01:06] [DEBUG] server=None, api=None [01:06] Starting ComfyUI server... [01:06] Starting ComfyUI server on port 41883... [01:06] Starting ComfyUI server on port 41883... [01:07] Waiting for server to be ready (timeout: 600s)... [01:09] [ComfyUI] [INFO] setup plugin alembic.autogenerate.schemas [01:09] [ComfyUI] [INFO] setup plugin alembic.autogenerate.tables [01:09] [ComfyUI] [INFO] setup plugin alembic.autogenerate.types [01:09] [ComfyUI] [INFO] setup plugin alembic.autogenerate.constraints [01:09] [ComfyUI] [INFO] setup plugin alembic.autogenerate.defaults [01:09] [ComfyUI] [INFO] setup plugin alembic.autogenerate.comments [01:09] [ComfyUI] [INFO] [01:09] [ComfyUI] Prestartup times for custom nodes: [01:09] [ComfyUI] [INFO] 0.0 seconds: D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\ComfyUI-GaussianPack [01:09] [ComfyUI] [INFO] [01:22] [ComfyUI] [INFO] Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': "ImportError: No module named 'triton'", 'capabilities': []} [01:22] [ComfyUI] [INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4']} [01:22] [ComfyUI] [INFO] Found comfy_kitchen backend cuda: {'available': False, 'disabled': True, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []} [01:22] [ComfyUI] [INFO] Checkpoint files will always be loaded safely. [01:22] [ComfyUI] [INFO] Total VRAM 16379 MB, total RAM 16379 MB [01:22] [ComfyUI] [INFO] pytorch version: 2.10.0+cpu [01:22] [ComfyUI] [INFO] Set vram state to: DISABLED [01:22] [ComfyUI] [INFO] Device: cpu [01:23] [ComfyUI] [INFO] Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention [01:31] [ComfyUI] [INFO] Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] [01:31] [ComfyUI] [INFO] ComfyUI version: 0.22.0 [01:31] [ComfyUI] [INFO] comfy-aimdo version: 0.4.5 [01:31] [ComfyUI] [INFO] comfy-kitchen version: 0.2.8 [01:31] [ComfyUI] [WARNING] ****** User settings have been changed to be stored on the server instead of browser storage. ****** [01:31] [ComfyUI] [WARNING] ****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ****** [01:31] [ComfyUI] [INFO] comfyui-frontend-package version: 1.44.19 [01:31] [ComfyUI] [INFO] comfyui-workflow-templates version: 0.9.82 [01:31] [ComfyUI] [INFO] comfyui-embedded-docs version: 0.5.1 [01:31] [ComfyUI] [INFO] comfy-kitchen version: 0.2.8 [01:31] [ComfyUI] [INFO] comfy-aimdo version: 0.4.5 [01:31] [ComfyUI] [INFO] [Prompt Server] web root: D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\.venv\Lib\site-packages\comfyui_frontend_package\static [01:31] [ComfyUI] [INFO] Asset seeder disabled [01:35] [ComfyUI] [INFO] loading... [01:35] [ComfyUI] [INFO] [01:35] [ComfyUI] Import times for custom nodes: [01:35] [ComfyUI] [INFO] 0.0 seconds: D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\websocket_image_save.py [01:35] [ComfyUI] [INFO] 0.0 seconds: D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\ComfyUI-validate-endpoint [01:35] [ComfyUI] [INFO] 0.0 seconds: D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\custom_nodes\ComfyUI-GaussianPack [01:35] [ComfyUI] [INFO] [01:35] [ComfyUI] [INFO] Context impl SQLiteImpl. [01:35] [ComfyUI] [INFO] Will assume non-transactional DDL. [01:35] [ComfyUI] [INFO] Context impl SQLiteImpl. [01:35] [ComfyUI] [INFO] Will assume non-transactional DDL. [01:35] [ComfyUI] [INFO] Running upgrade -> 0001_assets, Initial assets schema [01:35] [ComfyUI] Revision ID: 0001_assets [01:35] [ComfyUI] Revises: None [01:35] [ComfyUI] Create Date: 2025-12-10 00:00:00 [01:35] [ComfyUI] [INFO] Running upgrade 0001_assets -> 0002_merge_to_asset_references, Merge AssetInfo and AssetCacheState into unified asset_references table. [01:35] [ComfyUI] [INFO] Running upgrade 0002_merge_to_asset_references -> 0003_add_metadata_job_id, Add system_metadata and job_id columns to asset_references. [01:35] [ComfyUI] Change preview_id FK from assets.id to asset_references.id. [01:35] [ComfyUI] [INFO] Database upgraded from None to 0003_add_metadata_job_id [01:35] [ComfyUI] [INFO] Using RAM pressure cache. [01:35] [ComfyUI] [INFO] Starting server [01:35] [ComfyUI] [01:35] [ComfyUI] [INFO] To see the GUI go to: http://127.0.0.1:41883 [01:35] Server responding, waiting for nodes to load... [01:55] Server is ready! [01:55] Checking for import errors in server logs... [01:55] No import errors detected [01:55] Found 739 registered nodes [01:55] [REGISTRATION] PASSED [01:55] [01:55] [4/5] INSTANTIATION [01:55] ---------------------------------------- [01:55] [DEBUG] server=, api= [01:55] Testing node constructors... [01:59] All 5 node(s) instantiated successfully! [01:59] [INSTANTIATION] PASSED [01:59] [01:59] [5/5] EXECUTION [01:59] ---------------------------------------- [01:59] [DEBUG] server=, api= [01:59] CPU runner - will execute 1 workflow(s) [01:59] Running 1 workflow(s) (all with videos)... [01:59] Installing screenshot dependencies (playwright, pillow)... [02:00] Packages installed, downloading chromium browser... [02:20] Screenshot dependencies installed successfully [02:25] Starting headless browser... [02:25] Downloading Mesa llvmpipe for Windows... [02:32] Copied opengl32.dll to Chromium dir [02:32] Copied libgallium_wgl.dll to Chromium dir [02:32] Using Mesa llvmpipe (desktop GL) -- multithreaded CPU rendering [02:32] [ComfyUI] [INFO] Using RAM pressure cache. [02:32] Capturing execution frames: merge_splats.json [02:32] [ComfyUI] [INFO] Using RAM pressure cache. [02:41] Frame 1 saved (frame_000.jpg, t=0.0s) [02:41] Validating workflow... [02:41] [ComfyUI] [INFO] === /validate endpoint called === [02:41] [ComfyUI] [INFO] Received JSON with keys: ['prompt'] [02:41] [ComfyUI] [INFO] Prompt has 4 nodes [02:41] [ComfyUI] [INFO] Node 1: LoadPLY [02:41] [ComfyUI] [INFO] Inputs: {"ply_file": "apple.ply"} [02:41] [ComfyUI] [INFO] Node 2: PreviewGaussians [02:41] [ComfyUI] [INFO] Inputs: {"fov_degrees": 50, "image_width": 512, "image_height": 512, "renderer": "spark", "transport_format": "ply", "ply_path": ["1", 0]} [02:41] [ComfyUI] [INFO] Node 3: GaussianMerge [02:41] Queuing workflow for execution... [02:41] [ComfyUI] [INFO] Inputs: {"target_count": 100000, "output_filename": "merged", "opacity_threshold": 0, "k": 24, "ply_path": ["1", 0]} [02:41] [ComfyUI] [INFO] Node 4: PreviewGaussians [02:41] [ComfyUI] [INFO] Inputs: {"fov_degrees": 50, "image_width": 512, "image_height": 512, "renderer": "spark", "transport_format": "ply", "ply_path": ["3", 0]} [02:41] [ComfyUI] [INFO] Generated prompt_id: b53215f6-1692-4e1d-ab79-0decff491fee [02:41] [ComfyUI] [INFO] Calling execution.validate_prompt()... [02:41] [ComfyUI] [INFO] Validation result: valid=True [02:41] [ComfyUI] [INFO] === Validation PASSED === [02:41] [ComfyUI] [INFO] got prompt [02:41] [ComfyUI] [INFO] LoadPLY: apple.ply -> D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\input\apple.ply [02:41] [ComfyUI] [INFO] GaussianMerge: 200000 -> 100000 splats (ratio=0.5000) via NanoGS MPMM on D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\input\apple.ply [02:41] Node executed (1 total), capturing... [02:42] Frame 2 saved (frame_001.jpg, t=0.5s) [02:42] [capture-node] freeze=185ms shot=172ms unfreeze=5ms saved=True [02:50] Frame 3 saved (frame_002.jpg, t=5.0s) [02:50] [capture-periodic] freeze=1929ms shot=2206ms unfreeze=4ms saved=True [04:03] [ComfyUI] Loading PLY: D:\a\comfy-gpu-ci\comfy-gpu-ci\test_workspaces\GaussianPack-1923\ComfyUI\input\apple.ply [04:03] [ComfyUI] Initial splats: 200000 [04:03] [ComfyUI] Pruned splats: 200000, target: 100000 [04:03] [ComfyUI] Opacity Mean: 0.53443545 Median: 0.48362076 [04:03] [ComfyUI] Pruning splats with opacity below 0.0000 [04:03] [ComfyUI] Original count: 200000, after opacity pruning: 200000 [04:03] [ComfyUI] After opacity pruning, 200000 splats remain. [04:03] [ComfyUI] Pass 1: 200000 splats [04:03] [ComfyUI] [04:08] [ComfyUI] Edge costs: 0%| | 0/27 [00:00