theroyallab/tabbyAPI
1
0
Fork 0
mirror of https://github.com/theroyallab/tabbyAPI.git synced 2026-04-29 10:42:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

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( disable_request_streaming: Optional[bool] = Field(
False, description=("Disable API request streaming (default: False).") 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( realtime_process_priority: Optional[bool] = Field(
False, False,
description=( description=(

3
config_sample.yml
View File

@@ -216,9 +216,6 @@ developer:
# Disable API request streaming (default: False). # Disable API request streaming (default: False).
disable_request_streaming: false disable_request_streaming: false
# Enable the torch CUDA malloc backend (default: False).
cuda_malloc_backend: false
# Set process to use a higher priority. # Set process to use a higher priority.
# For realtime process priority, run as administrator or sudo. # For realtime process priority, run as administrator or sudo.
# Otherwise, the priority will be set to high. # Otherwise, the priority will be set to high.