jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Config: Remove developer arg cuda_malloc_backend

Browse source 
* cudaMallocAsync is now enabled by default on supported configurations
This commit is contained in:
DocShotgun 2025-08-01 10:59:13 -07:00
parent 113643c0df
commit 102af306e5
2 changed files with 0 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

3
common/config_models.py
View file

@ -419,9 +419,6 @@ class DeveloperConfig(BaseConfigModel):
disable_request_streaming: Optional[bool] = Field(
False, description=("Disable API request streaming (default: False).")
)
cuda_malloc_backend: Optional[bool] = Field(
False, description=("Enable the torch CUDA malloc backend (default: False).")
)
realtime_process_priority: Optional[bool] = Field(
False,
description=(