#3289 The Engine stopped it self because it had stopped making progress

Descripción

[strata] other apps use the Chat settings: reasoning_effort=high
ready: http://127.0.0.1:8080/v1  (OpenAI: /v1/chat/completions, Anthropic: /v1/messages, context 131072 tokens)
       open http://127.0.0.1:8080/ in a browser to chat; close this window to stop the model
       from other devices: http://192.168.2.60:8080/   (API: http://192.168.2.60:8080/v1)
       from other devices: http://192.168

[strata-iq2_xs.log](https://github.com/user-attachments/files/33690778/strata-iq2_xs.log)

.3.60:8080/   (API: http://192.168.3.60:8080/v1)
       WARNING: no API key - anyone on your network can use this model. Add "api_key": "..." to the config (clients send it as their API key; the web page asks for it)
       nothing arrives? Windows Firewall blocks it until allowed: accept its prompt for Python, or run in an admin PowerShell:
         New-NetFirewallRule -DisplayName "Strata 8080" -Direction Inbound -Protocol TCP -LocalPort 8080 -Action Allow -Profile Private
       (and set this network to Private in Windows' network settings)
[strata] reading the prompt: 30,046 tokens, 10 s so far
[strata] reading the prompt: 30,046 tokens, 20 s so far
[strata] reading the prompt: 30,046 tokens, 30 s so far
[strata] reading the prompt: 30,046 tokens, 40 s so far
[strata] reading the prompt: 30,046 tokens, 50 s so far
[strata] reading the prompt: 30,046 tokens, 60 s so far
[strata] reading the prompt: 30,046 tokens, 70 s so far
[strata] the engine stopped unexpectedly (exit code 3221226505). The engine stopped itself because it had stopped making progress - a hang it caught. Its log line: strata serve: no progress for 60 s during a request (reading the prompt (batched): waiting for the GPU (attention, router) at layer 7 of the prompt chunk from token 0) - stopping the engine so the server starts it again (issue #29) - please report it at github.com/Niko1221/Strata/issues. The next request starts the engine again. Its log: D:\Strata-main\strata-iq2_xs.log
[strata] done: 0 tokens in 72 s (0.0 tok/s) (error, cancel=False)
[strata] the engine had stopped (exit code 3221226505); starting it again (a minute or two) ...
[strata] starting the engine: reading the model's weights ...
[strata] loading the experts the GPU does not hold into RAM (of about 39 GB) and locking part of them for the GPU.
         YOUR PC CAN BE SLOW OR STOP RESPONDING FOR 1-3 MINUTES NOW - this is normal.
         Please wait and don't close this window; the browser opens when it is ready.
[strata] filling the GPU's expert cache (16741 experts, 22.45 GiB of VRAM) ...
[strata] still starting (27 s) - please wait ...
[strata] still starting (47 s) - please wait ...
[strata] the engine is running again
[strata] reading the prompt: 30,046 tokens, 10 s so far
[strata] reading the prompt: 30,046 tokens, 20 s so far
[strata] the engine stopped unexpectedly (exit code 3221226505). The engine stopped itself because it had stopped making progress - a hang it caught. Its log line: strata serve: no progress for 60 s during a request (reading the prompt (batched): waiting for the GPU (attention, router) at layer 39 of the prompt chunk from token 0) - stopping the engine so the server starts it again (issue #29) - please report it at github.com/Niko1221/Strata/issues. The next request starts the engine again. Its log: D:\Strata-main\strata-iq2_xs.log
[strata] done: 0 tokens in 100 s (0.0 tok/s) (error, cancel=False)
[strata] the engine had stopped (exit code 3221226505); starting it again (a minute or two) ...
[strata] starting the engine: reading the model's weights ...
[strata] loading the experts the GPU does not hold into RAM (of about 39 GB) and locking part of them for the GPU.
         YOUR PC CAN BE SLOW OR STOP RESPONDING FOR 1-3 MINUTES NOW - this is normal.
         Please wait and don't close this window; the browser opens when it is ready.
[strata] filling the GPU's expert cache (16741 experts, 22.45 GiB of VRAM) ...
[strata] still starting (27 s) - please wait ...
[strata] still starting (47 s) - please wait ...
[strata] almost ready ...
[strata] the engine is running again
[strata] done: 0 tokens in 16 s (0.0 tok/s) (cancel, cancel=True)
[strata] done: 0 tokens in 91 s (0.0 tok/s) (cancel, cancel=True)
[strata] the engine had stopped (exit code 3221226505); starting it again (a minute or two) ...
[strata] starting the engine: reading the model's weights ...
[strata] loading the experts the GPU does not hold into RAM (of about 39 GB) and locking part of them for the GPU.
         YOUR PC CAN BE SLOW OR STOP RESPONDING FOR 1-3 MINUTES NOW - this is normal.
         Please wait and don't close this window; the browser opens when it is ready.
[strata] filling the GPU's expert cache (16741 experts, 22.45 GiB of VRAM) ...
[strata] still starting (27 s) - please wait ...