comfyui server unresponsed after a same workflow several times finished and background python.exe cant kill,i must restart my pc to run comfyui again

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

run normally or throw exception

### Actual Behavior

api timed out HTTPConnectionPool(host='127.0.0.1', port=8188): Read timed out. (read timeout=30)
console has no message, just normal

### Steps to Reproduce

every workflow happens, maybe run one time,maybe run 7 or 8 times workflow,then web cant response, operation fail.

### Debug Logs

```powershell
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
[INFO] Disabling intermediate node cache.
[INFO] Starting server

[INFO] To see the GUI go to: http://0.0.0.0:8188
[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 This is likely caused by a custom node extension using outdated APIs.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: /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 This is likely caused by a custom node extension using outdated APIs.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: /extensions/core/clipspace.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 This is likely caused by a custom node extension using outdated APIs.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 This is likely caused by a custom node extension using outdated APIs.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.
[INFO] [vsLinx] Combo type fix enabled via settings.
[INFO] [vsLinx] Combo type fix enabled via settings.
[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 This is likely caused by a custom node extension using outdated APIs.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.
[INFO] [ComfyUI-Manager] The ComfyRegistry cache update is still in progress, so an outdated cache is being used.
FETCH DATA from: H:\ComfyUI\python_embeded\Lib\site-packages\comfyui_manager\custom-node-list.json [DONE]
[INFO] got prompt
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: mxfp8, nvfp4, float8_e5m2, float8_e4m3fn
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLUX
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[WARNING] no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.
[INFO] Requested to load VideoVAE
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Found quantization metadata version 1
[INFO] Using MixedPrecisionOps for text encoder
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] Using sage attention mode: auto
[INFO] Requested to load LTXAVTEModel_
[INFO] Model LTXAVTEModel_ prepared for dynamic VRAM loading. 11200MB Staged. 0 patches attached. Force pre-loaded 400 weights: 1749 KB.
[INFO] Model LTXAVTEModel_ prepared for dynamic VRAM loading. 11200MB Staged. 0 patches attached. Force pre-loaded 400 weights: 1749 KB.
Shape of the first 'weight' key (diffusion_model.adaln_single.emb.timestep_embedder.linear_1.lora_A.weight): torch.Size([1, 256])
Shape of the first 'weight' key (diffusion_model.adaln_single.emb.timestep_embedder.linear_1.lora_A.weight): torch.Size([1, 256])
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 183969054443544 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "183969054443544" and server-generated random seed won't be cached.
[rgthree-comfy][Seed] Cannot save server-generated seed to image workflow metadata because workflow was not provided.
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 28786MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|██████████████████████████████████████████████████████████████████████████████████| 12/12 [03:12<00:00, 16.04s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] Requested to load VideoVAE
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] Requested to load VideoVAE
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
Shape of the first 'weight' key (diffusion_model.adaln_single.emb.timestep_embedder.linear_1.lora_A.weight): torch.Size([1, 256])
Shape of the first 'weight' key (diffusion_model.adaln_single.emb.timestep_embedder.linear_1.lora_A.weight): torch.Size([1, 256])
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 28786MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
75%|███████████████████████████████████████████████████████████████ | 3/4 [04:41<01:29, 89.40s/it][INFO] got prompt
100%|████████████████████████████████████████████████████████████████████████████████████| 4/4 [06:09<00:00, 92.26s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] Requested to load VideoVAE
[INFO] 0 models unloaded.
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Prompt executed in 00:10:33
```

### Other
api timed out HTTPConnectionPool(host='127.0.0.1', port=8188): Read timed out. (read timeout=30)
_No response_

The report names no repository files, tests, or entry points. Start by reproducing the timeout after repeated workflow runs and inspecting the server/API behavior using the supplied logs; done would require identifying the cause and verifying a fix with a regression test or equivalent evidence.

Written by the indexing model from the issue text.