chore(deps): bump torch and diffusers (#5970)

* chore(ci): add backend build tests

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

* chore(deps): bump torch and diffusers

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

* chore(ci): run diffusers/hipblas on self-hosted

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

* chore(ci): do not publish darwin if building from PRs

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

---------

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

.github/workflows/backend.yml

@@ -2,6 +2,7 @@
 name: 'build backend container images'
 
 on:
+  pull_request:
   push:
     branches:
       - master
@@ -325,7 +326,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-rocm-hipblas-diffusers'
-            runs-on: 'ubuntu-latest'
+            runs-on: 'arc-runner-set'
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             skip-drivers: 'false'
             backend: "diffusers"
@@ -955,6 +956,7 @@ jobs:
           path: build/llama-cpp.tar
   llama-cpp-darwin-publish:
     needs: llama-cpp-darwin
+    if: github.event_name != 'pull_request'
     runs-on: ubuntu-latest
     steps:
       - name: Download llama-cpp.tar
@@ -1043,6 +1045,7 @@ jobs:
           name: llama-cpp-tar-x86
           path: build/llama-cpp.tar
   llama-cpp-darwin-x86-publish:
+    if: github.event_name != 'pull_request'
     needs: llama-cpp-darwin-x86
     runs-on: ubuntu-latest
     steps: