fix UI keycloak var, gpu_runtime

defenseunicorns · Sep 5, 2024 · 3134908 · 3134908
1 parent 1b4df8e
commit 3134908
Show file tree

Hide file tree

Showing 10 changed files with 15 additions and 15 deletions.
diff --git a/Makefile b/Makefile
@@ -304,8 +304,8 @@ silent-deploy-gpu:
 	@$(MAKE) -j${MAX_JOBS} \
 		silent-deploy-api-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS}" \
 		silent-deploy-vllm-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS}" \
-		silent-deploy-text-embeddings-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS} --set=GPU_RUNTIME_NAME='nvidia'" \
-		silent-deploy-whisper-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS} --set=GPU_RUNTIME_NAME='nvidia'"
+		silent-deploy-text-embeddings-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS} --set=GPU_RUNTIME='nvidia'" \
+		silent-deploy-whisper-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS} --set=GPU_RUNTIME='nvidia'"
 	@echo "Deploying UI..."
 	@$(MAKE) silent-deploy-ui-package ZARF_FLAGS="${ZARF_FLAGS} ${SILENT_ZARF_FLAGS} --set=MODEL='vllm'"
 	@echo "All deployments completed"

diff --git a/bundles/dev/cpu/uds-config.yaml b/bundles/dev/cpu/uds-config.yaml
@@ -1,10 +1,10 @@
 variables:
   text-embeddings:
-    GPU_RUNTIME_NAME: "" # Leave blank if nvidia runtimeClass is not present in cluster
+    gpu_runtime: "" # Leave blank if nvidia runtimeClass is not present in cluster
     gpu_limit: 0
 
   whisper:
-    GPU_RUNTIME_NAME: "" # Leave blank if nvidia runtimeClass is not present in cluster
+    gpu_runtime: "" # Leave blank if nvidia runtimeClass is not present in cluster
     gpu_limit: 0
 
   supabase:

diff --git a/bundles/dev/gpu/uds-config.yaml b/bundles/dev/gpu/uds-config.yaml
@@ -1,11 +1,11 @@
 # see individual zarf packaging configuration for more variables and variable descriptions
 variables:
   text-embeddings:
-    GPU_RUNTIME_NAME: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
+    gpu_runtime: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
     gpu_limit: 0  # runs on CPU until GPU limit is increased
 
   whisper:
-    GPU_RUNTIME_NAME: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
+    gpu_runtime: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
     gpu_limit: 0  # runs on CPU until GPU limit is increased
 
   vllm:

diff --git a/bundles/latest/cpu/uds-config.yaml b/bundles/latest/cpu/uds-config.yaml
@@ -1,11 +1,11 @@
 # see individual zarf packaging configuration for more variables and variable descriptions
 variables:
   text-embeddings:
-    GPU_RUNTIME_NAME: "" # Leave blank if nvidia runtimeClass is not present in cluster
+    gpu_runtime: "" # Leave blank if nvidia runtimeClass is not present in cluster
     gpu_limit: 0
 
   whisper:
-    GPU_RUNTIME_NAME: "" # Leave blank if nvidia runtimeClass is not present in cluster
+    gpu_runtime: "" # Leave blank if nvidia runtimeClass is not present in cluster
     gpu_limit: 0
 
   supabase:

diff --git a/bundles/latest/gpu/uds-config.yaml b/bundles/latest/gpu/uds-config.yaml
@@ -1,11 +1,11 @@
 # see individual zarf packaging configuration for more variables and variable descriptions
 variables:
   text-embeddings:
-    GPU_RUNTIME_NAME: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
+    gpu_runtime: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
     gpu_limit: 0  # runs on CPU until GPU limit is increased
 
   whisper:
-    GPU_RUNTIME_NAME: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
+    gpu_runtime: "nvidia"  # Set to ensure the nvidia runtimeClass is present in case GPU limit is increased
     gpu_limit: 0  # runs on CPU until GPU limit is increased
 
   vllm:

diff --git a/packages/text-embeddings/zarf.yaml b/packages/text-embeddings/zarf.yaml
@@ -16,7 +16,7 @@ variables:
     description: The GPU limit for the model inferencing.
     default: "0"
     pattern: "^[0-9]+$"
-  - name: GPU_RUNTIME_NAME
+  - name: GPU_RUNTIME
     description: The GPU class name for the model inferencing. Leave blank for CPU-only.
     default: ""
     pattern: "^(nvidia)?$"

diff --git a/packages/ui/values/upstream-values.yaml b/packages/ui/values/upstream-values.yaml
@@ -18,7 +18,7 @@ env:
   - name: PUBLIC_SUPABASE_URL
     value: "https://supabase-kong.###ZARF_VAR_DOMAIN###"
   - name: PUBLIC_DISABLE_KEYCLOAK
-    value: "true"
+    value: "###ZARF_VAR_DISABLE_KEYCLOAK###"
   - name: PUBLIC_MESSAGE_LENGTH_LIMIT
     value: "10000"
   - name: SUPABASE_AUTH_EXTERNAL_KEYCLOAK_URL

diff --git a/packages/ui/zarf.yaml b/packages/ui/zarf.yaml
@@ -16,7 +16,7 @@ variables:
     prompt: true
     sensitive: true
   - name: OPENAI_API_KEY
-    description: OpenAI API Key. If specified, app will use OpenAI instead of LeapfrogAI
+    description: OpenAI API key - if specified, the UI will use OpenAI instead of LeapfrogAI
     prompt: true
     default: ""
     sensitive: true

diff --git a/packages/vllm/zarf.yaml b/packages/vllm/zarf.yaml
@@ -15,7 +15,7 @@ variables:
     description: The GPU limit for the model inferencing. Must be 1 or more.
     default: "1"
     pattern: "^[1-9][0-9]*$"
-  - name: GPU_RUNTIME_NAME
+  - name: GPU_RUNTIME
     description: The GPU runtime name for the model inferencing.
     default: "nvidia"
     pattern: "^(nvidia)?$"

diff --git a/packages/whisper/zarf.yaml b/packages/whisper/zarf.yaml
@@ -16,7 +16,7 @@ variables:
     description: The GPU limit for the model inferencing.
     default: "0"
     pattern: "^[0-9]+$"
-  - name: GPU_RUNTIME_NAME
+  - name: GPU_RUNTIME
     description: The GPU runtime name for the model inferencing. Leave blank for CPU-only.
     default: ""
     pattern: "^(nvidia)?$"