mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-05-08 03:41:13 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix: race during stop of active backends (#5106)

Browse Source 
* chore: drop double call to stop all backends, refactors

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: do lock when cycling to models to delete

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-04-01 00:01:10 +02:00
committed by GitHub
parent 2f9203cd2a
commit 05f7004487
4 changed files with 45 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env
+3
View File
@@ -29,6 +29,9 @@
## Enable/Disable single backend (useful if only one GPU is available)
# LOCALAI_SINGLE_ACTIVE_BACKEND=true
# Forces shutdown of the backends if busy (only if LOCALAI_SINGLE_ACTIVE_BACKEND is set)
# LOCALAI_FORCE_BACKEND_SHUTDOWN=true
## Specify a build type. Available: cublas, openblas, clblas.
## cuBLAS: This is a GPU-accelerated version of the complete standard BLAS (Basic Linear Algebra Subprograms) library. It's provided by Nvidia and is part of their CUDA toolkit.
## OpenBLAS: This is an open-source implementation of the BLAS library that aims to provide highly optimized code for various platforms. It includes support for multi-threading and can be compiled to use hardware-specific features for additional performance. OpenBLAS can run on many kinds of hardware, including CPUs from Intel, AMD, and ARM.