node down?: minimaxh3memoryefficientsageattentionpatch

yesterday works, today no

-

=== ComfyUI 0.31.0 | torch 2.13.0+cu130 ===
(para pararlo: bash /workspace/comfy_rp.sh stop | Ctrl+C NO sirve)

[INFO] setup plugin alembic.autogenerate.schemas
[INFO] setup plugin alembic.autogenerate.tables
[INFO] setup plugin alembic.autogenerate.types
[INFO] setup plugin alembic.autogenerate.constraints
[INFO] setup plugin alembic.autogenerate.defaults
[INFO] setup plugin alembic.autogenerate.comments
[INFO] setup plugin alembic.autogenerate.checkconstraint_byname
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-08-09 15:19:09.641
** Platform: Linux
** Python version: 3.12.3 (main, Mar 23 2026, 19:04:32) [GCC 13.3.0]
** Python executable: /workspace/runpod-slim/ComfyUI/.venv-cu128/bin/python
** ComfyUI Path: /workspace/runpod-slim/ComfyUI
** ComfyUI Base Folder Path: /workspace/runpod-slim/ComfyUI
** User directory: /workspace/runpod-slim/ComfyUI/user
** ComfyUI-Manager config path: /workspace/runpod-slim/ComfyUI/user/__manager/config.ini
** Log path: /workspace/runpod-slim/ComfyUI/user/comfyui.log
[INFO]
Prestartup times for custom nodes:
[INFO] 1.8 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Manager
[INFO]
[INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_embedding', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'gemv_awq_w4a16', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'gemv_awq_w4a16', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'na3d', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend hip: {'available': False, 'disabled': False, 'unavailable_reason': 'PyTorch ROCm/HIP runtime not available', 'capabilities': []}
[INFO] Checkpoint files will always be loaded safely.
[INFO] Total VRAM 32109 MB, total RAM 386609 MB
[INFO] pytorch version: 2.13.0+cu130
[INFO] Enabled fp16 accumulation.
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 347948.0
[INFO] Using sage attention
[INFO] aimdo: /project/src/control.c:276:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 5090 (VRAM: 32109 MB)
[INFO] DynamicVRAM support detected and enabled
[INFO] Python version: 3.12.3 (main, Mar 23 2026, 19:04:32) [GCC 13.3.0]
[INFO] ComfyUI version: 0.31.0
[INFO] comfy-aimdo version: 0.4.13
[INFO] comfy-kitchen version: 0.2.28
[INFO] comfyui-frontend-package version: 1.48.7
[INFO] comfyui-workflow-templates version: 0.11.37
[INFO] comfyui-embedded-docs version: 0.5.9
[INFO] comfy-kitchen version: 0.2.28
[INFO] comfy-aimdo version: 0.4.13
[INFO] [Prompt Server] web root: /workspace/runpod-slim/ComfyUI/.venv-cu128/lib/python3.12/site-packages/comfyui_frontend_package/static
[INFO] Asset seeder disabled
[INFO] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
------------------------------
[Civicomfy Config Initialized]
- Plugin Root: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy
- Web Directory: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy/web
- ComfyUI Base Path: /workspace/runpod-slim/ComfyUI
------------------------------
[Civicomfy Manager] Warning: ComfyUI folder_paths not available. Path validation/opening might be limited.
[Manager] History file not found (/workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy/download_history.json). Starting with empty history.
Civitai Download Manager starting (Max Concurrent: 3).
[Manager] Process queue thread started.
[Civicomfy] All server route modules loaded.
[Civicomfy] Core modules imported successfully.
------------------------------
--- Civicomfy Custom Extension Loaded ---
- Serving frontend files from: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy/web (Relative: ./web)
- Download Manager Initialized: Yes
- API Endpoints Registered: Yes
- Frontend files found.
- Look for 'Civicomfy' button in the ComfyUI menu.
------------------------------
[Civicomfy] Verified model type directories:
- checkpoint: /workspace/runpod-slim/ComfyUI/models/checkpoints
- diffusionmodels: /workspace/runpod-slim/ComfyUI/models/unet
- unet: /workspace/runpod-slim/ComfyUI/models/unet
- lora: /workspace/runpod-slim/ComfyUI/models/loras
- locon: /workspace/runpod-slim/ComfyUI/models/loras
- lycoris: /workspace/runpod-slim/ComfyUI/models/loras
- vae: /workspace/runpod-slim/ComfyUI/models/vae
- embedding: /workspace/runpod-slim/ComfyUI/models/embeddings
- hypernetwork: /workspace/runpod-slim/ComfyUI/models/hypernetworks
- controlnet: /workspace/runpod-slim/ComfyUI/models/controlnet
- upscaler: /workspace/runpod-slim/ComfyUI/models/upscale_models
- motionmodule: /workspace/runpod-slim/ComfyUI/models/motion_models
- poses: /workspace/runpod-slim/ComfyUI/models/poses
- wildcards: /workspace/runpod-slim/ComfyUI/models/wildcards
- other: /workspace/runpod-slim/ComfyUI/models/other
[INFO] ### Loading: ComfyUI-Manager (V3.41)
[INFO] [ComfyUI-Manager] network_mode: public
[INFO] [ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
[INFO] ### ComfyUI Version: v0.31.0-8-gcbbc9dab | Released on '2026-08-08'
[INFO] [RunpodDirect] Cgroup RAM patch enabled: host=377.55 GiB, limit=87.54 GiB, available=27.26 GiB
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[INFO]
Import times for custom nodes:
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/websocket_image_save.py
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-RunpodDirect
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/Civicomfy
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Spectrum-MiniMax-H3
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-KJNodes
[INFO] 0.0 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-SolAttn_triton
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-Manager
[INFO] 0.1 seconds: /workspace/runpod-slim/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
[INFO]
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[INFO] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[INFO] Using RAM pressure cache.
[INFO] Starting server

[INFO] To see the GUI go to: http://0.0.0.0:8188
FETCH ComfyRegistry Data: 5/170
FETCH ComfyRegistry Data: 10/170
FETCH ComfyRegistry Data: 15/170
FETCH ComfyRegistry Data: 20/170
FETCH ComfyRegistry Data: 25/170
FETCH ComfyRegistry Data: 30/170
FETCH ComfyRegistry Data: 35/170
FETCH ComfyRegistry Data: 40/170
FETCH ComfyRegistry Data: 45/170
FETCH ComfyRegistry Data: 50/170
FETCH ComfyRegistry Data: 55/170
FETCH ComfyRegistry Data: 60/170
FETCH ComfyRegistry Data: 65/170
FETCH ComfyRegistry Data: 70/170
FETCH ComfyRegistry Data: 75/170
FETCH ComfyRegistry Data: 80/170
FETCH ComfyRegistry Data: 85/170
FETCH ComfyRegistry Data: 90/170
FETCH ComfyRegistry Data: 95/170
FETCH ComfyRegistry Data: 100/170
FETCH ComfyRegistry Data: 105/170
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 110/170
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 115/170
FETCH ComfyRegistry Data: 120/170
FETCH ComfyRegistry Data: 125/170
^CFETCH ComfyRegistry Data: 130/170
FETCH ComfyRegistry Data: 135/170
FETCH ComfyRegistry Data: 140/170
FETCH ComfyRegistry Data: 145/170
FETCH ComfyRegistry Data: 150/170
FETCH ComfyRegistry Data: 155/170
FETCH ComfyRegistry Data: 160/170
FETCH ComfyRegistry Data: 165/170
FETCH ComfyRegistry Data: 170/170
FETCH ComfyRegistry Data [DONE]
[INFO] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[INFO] [ComfyUI-Manager] All startup tasks have been completed.

Start by reproducing the reported failure in ComfyUI 0.31.0 with torch 2.13.0+cu130 on the listed NVIDIA RTX 5090 environment. Read the startup output around ComfyUI-Spectrum-MiniMax-H3, sage attention, comfy-aimdo, and comfy-kitchen, then compare with the custom-node extensions shown in the log. Done means identifying the change that caused the node to stop working and confirming a reproducible fix.

Written by the indexing model from the issue text.