mirrors/nextcloud-documentation
3
0
Fork 0
mirror of https://github.com/nextcloud/documentation.git synced 2025-10-26 11:18:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(admin_manual): Make capacity estimates more skeptical

Browse Source 
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
This commit is contained in:
Marcel Klehr 2024-03-26 10:39:50 +01:00
parent 26a60c4295
commit 91b8e2f3e5
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
admin_manual/ai/app_context_chat.rst
View File

@ -50,7 +50,7 @@ Installation
Scaling
-------
It is currently not possible to scale ExApps like Context Chat, we are working on this. One instance has a rough capacity of 1000 user queries per hour.
It is currently not possible to scale ExApps like Context Chat, we are working on this. Based on our calculations an instance has a rough capacity of 1000 user requests per hour. However, this number is based on theory and we do appreciate real-world feedback on this.
App store
---------

2
admin_manual/ai/app_llm2.rst
View File

@ -52,7 +52,7 @@ This app allows supplying alternate LLM models as *gguf* files in the ``/nc_app_
Scaling
-------
It is currently not possible to scale this app, we are working on this. One instance has a rough capacity of 1000 user queries per hour.
It is currently not possible to scale this app, we are working on this. Based on our calculations an instance has a rough capacity of 1000 user requests per hour. However, this number is based on theory and we do appreciate real-world feedback on this.
App store
---------

2
admin_manual/ai/app_stt_whisper2.rst
View File

@ -54,7 +54,7 @@ This app allows supplying alternate LLM models as *gguf* files in the ``/nc_app_
Scaling
-------
It is currently not possible to scale this app, we are working on this. One instance has a rough capacity of 4h of transcription throughput per minute (measured with 8 CPU threads on an Intel(R) Xeon(R) Gold 6226R).
It is currently not possible to scale this app, we are working on this. Based on our calculations an instance has a rough capacity of 4h of transcription throughput per minute (measured with 8 CPU threads on an Intel(R) Xeon(R) Gold 6226R). It is unclear how close to real-world usage this number is, so we do appreciate real-world feedback on this.
App store
---------