theroyallab/tabbyAPI
1
0
Fork 0
mirror of https://github.com/theroyallab/tabbyAPI.git synced 2026-04-20 14:28:54 +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

9
common/config_models.py
View File

@@ -265,12 +265,13 @@ class ModelConfig(BaseConfigModel):
),
gt=0,
)
disable_output_chunking: Optional[bool] = Field(
False,
output_chunking: Optional[bool] = Field(
True,
description=(
"Disable output chunking (default: false).\n"
"Use output chunking (default: True)\n"
"Instead of allocating cache space for the entire completion at once, "
"allocate in chunks as needed.\n"
"Used by EXL3 models only.\n"
"True, allocate space in the cache for the entire response with each request..\n"
),
)
max_batch_size: Optional[int] = Field(