38a04fbda1
swap_stopper, do not let the echo prevent the function from returning an unclean status.
me2026-10-24 12:39:56 -07:00
4342b8842f
swap_stopper, ensure ollama dies even if it is not being run through runit.
me2026-10-24 12:35:27 -07:00
ef9566c76c
llm, move some functions to env-shared project.
me2026-10-24 10:55:11 -07:00
41f306f7d7
llm, add another alias for restarting AI services.
me2026-10-23 19:03:16 -07:00
4c5d753b73
vscode, ensure new files are opened at the end.
me2026-10-23 17:44:19 -07:00
fcf77e22c5
llm, adjust the prompts.
me2026-10-23 17:44:00 -07:00
75503d762b
llm, extend keep alive time again since context gets unloaded too, remove DEBUG output from ollama log, use .bashrc rather than profiles since Docker is not creating those, create AGENTS.md in user root, make the JDK directory read only to prevent AI from tampering.
me2026-10-23 17:43:48 -07:00
e0b1fa30f1
java, go down to 17 like being used in development.
me2026-10-23 17:41:31 -07:00
d7eed3c883
llm, update PATH wording since it has been taken care of.
me2026-10-22 18:04:05 -07:00
c341d216ad
llm, maintain env vars and PATH changes in the AI Sandbox folder.
me2026-10-22 18:03:32 -07:00
f6fd08f966
llm, add a safeguard when a model causes swap-stopper to reset ollama.
me2026-10-22 11:58:16 -07:00
295b6b3d19
android, allow the licenses check to fail on newer SDKs.
me2026-10-22 11:57:44 -07:00
0363aefc1d
Merge branch 'dev2' into dev Pushed on a system when another system still needed to push.
me2026-10-21 09:58:43 -07:00
e81de0c63b
llm, add more performance tests to markdown file.
me2026-10-21 09:56:47 -07:00
d5e3a57f56
llm, add a few models for mistral-small4 but they are too large or not the correct format for ollama, a few more edits to ollama_threads.
me2026-10-21 09:56:14 -07:00
99a0b7ca0b
provision, fix the MCP block overwriting the GUI block.
me2026-10-21 09:48:42 -07:00
a47d5fd129
tunnel, move service task to block and change block to be for runit.
me2026-10-21 09:45:14 -07:00
472f7921e7
tunnel, fix location of facts.
me2026-10-21 09:40:47 -07:00
9a2e4ca4d2
i3, move gnome-system-monitor to WS10, btop on WS1.
me2026-10-21 08:51:35 -07:00
eb761e41dc
roleplays, rename Quick Coder to Coder MoE in both title and ID.
me2026-10-21 08:20:41 -07:00
05e2244efb
roleplays, add a language entry for qwen3.5:35b since it is MoE and is not code-scoped like qwen3.6.
me2026-10-21 08:19:48 -07:00
bd7112e8d5
llm, filter out the less useful tests in ollama_threads. Should help save a lot of time, maybe up to 60-75% since they were the slower ones.
me2026-10-21 07:27:28 -07:00
40d9a7252e
llm, if Internet is available, pull extra packages for open-terminal.
me2026-10-21 06:06:41 -07:00
6482dd123d
llm, change ollama_threads to use a better method of determining the number of cores to test, also fix output.
me2026-10-21 05:43:37 -07:00
74789ba70c
roleplays, go up to 7 threads due to benchmark data. 8 is very marginal, leave it for the system. 4 is great for MoE tokens/sec but 7 is still a bit faster in overall response time.
me2026-10-21 05:28:05 -07:00
6411d4792a
roleplays, download the current state.
me2026-10-21 05:26:35 -07:00
e367e9e14b
llm, begin populating thread benchmark data.
me2026-10-21 05:23:57 -07:00
c604859947
llm, add elapsed time to ollama_threads.
me2026-10-21 05:23:41 -07:00
7f7f2a2edb
llm, fix context sending in ollama_threads.
me2026-10-21 04:55:01 -07:00
92be32345a
llm, add context param to ollama_threads.
me2026-10-21 04:51:46 -07:00
5719ec6b60
llm, add optional open-terminal package list, helpful but required Internet, may have to do an Internet check and then choose which docker run command to execute. Also fix and enhance the ollama_thread checker.
me2026-10-21 04:47:16 -07:00
85e60ef60c
llm, improve the thread testing output and also make the the ansible variable is always an int.
me2026-10-21 03:03:24 -07:00
5620e5a223
llm, add function for benchmarking whether more threads adds latency.
me2026-10-21 02:57:12 -07:00
4fd12ce45e
llm, add details about the workstation being used.
me2026-10-21 02:43:07 -07:00
5c67da3eb8
roleplays, delete old IDs, change to use 6 cores leaving 1 physical for the system and 1 for the user (in theory, of course).
me2026-10-21 02:42:44 -07:00
14fdc1f740
llm, add more size testing data.
me2026-10-21 02:32:55 -07:00
1adf4db6ee
llm, wrap the personality prompts.
me2026-10-21 02:30:04 -07:00
3b3c7bd501
Place the personality prompts into a knowledge base and attach them to the roleplays so that they can be maintained in a more centralized manner
me2026-10-21 02:29:03 -07:00
b5e5a18e4c
roleplays, fix the IDs, will import back into Open WebUI.
me2026-10-21 02:05:34 -07:00
870a99804a
llm, add OLLAMA_NUM_THREADS which was proposed but rejected so far.
me2026-10-21 02:03:37 -07:00
358bf9e11d
roleplays, set max thread count to number of physical cores rather than using the emulated cores too.
me2026-10-21 02:03:03 -07:00
20549e0055
roleplays, ensure everyone has tags, add providers for remaining ministral weights.
me2026-10-20 17:40:32 -07:00
003e8d8430
roleplays, add an entry coder based on codestral since it does not swell up like devstral.
me2026-10-20 17:28:44 -07:00
0e990e2ed5
roleplays, ensure models have all functionality.
me2026-10-20 17:18:53 -07:00
2ff0ccd392
llm.md, finish the prompts for now.
me2026-10-20 17:10:13 -07:00
9a9eb8b8e6
roleplays, add current Open WebUI lineup.
me2026-10-20 17:09:54 -07:00
bec4c919d4
llm, stop using pull=always because then network is required to start the container.
me2026-10-20 16:36:44 -07:00
1ad4f642db
llm, continue working on the prompts.
me2026-10-20 11:56:23 -07:00
52d7ae3d86
llm, move bulk comments to an md file and start adding prompts to use in Open WebUI.
me2026-10-20 10:16:40 -07:00
2dccea21ae
root, set the mode directly to avoid lint issues.
me2026-10-17 17:18:51 -07:00
32916ad470
header, name most the include_tasks and reorder based on subgroups, refactoring a few file locations in some instances.
me2026-10-17 17:17:49 -07:00
36a80041f3
llm, no longer bother with autocomplete in Continue, not getting any functionality since on 100% CPU so it's just draining resources.
me2026-10-17 14:37:03 -07:00
9f82c136e9
llm, add open-terminal as a test bed for Open WebUI LLMs, so that they can read/write files and execute commands in a safe way.
me2026-10-17 13:08:50 -07:00
89fdb52fcc
llm, move Docker section out of Open WebUI since it's now shared.
me2026-10-17 13:08:12 -07:00
98c6d47d7f
provision, add params for open-terminal, plus an optional key for qwen code.
me2026-10-17 12:55:27 -07:00
8a2a723d4b
llm, continue dropping keep alive since tools which use LLMs correctly manage this themselves.
me2026-10-17 12:01:57 -07:00