theroyallab/tabbyAPI
1
0
Fork 0
mirror of https://github.com/theroyallab/tabbyAPI.git synced 2026-03-15 00:07:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

Config: replace disable_output_chunking flag with output_chunking

Browse Source
This commit is contained in:
turboderp
2025-10-14 02:47:52 +02:00
parent 7eee3924c7
commit 8abdfe7b13
4 changed files with 11 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
config_sample.yml
View File

@@ -133,10 +133,10 @@ model:
# An ideal value is between 512 and 4096.
chunk_size: 2048
# Disable output chunking (default: false)
# Use output chunking (default: True)
# Instead of allocating cache space for the entire completion at once, allocate in chunks as needed.
# Used by EXL3 models only.
# If True, allocate space in the cache for the entire response with each request.
disable_output_chunking: false
output_chunking: true
# Set the maximum number of prompts to process at one time (default: None/Automatic).
# Automatically calculated if left blank.