From 313490819fbcada8eb6ca7fef140d08997299fe9 Mon Sep 17 00:00:00 2001 From: Justin Law Date: Thu, 5 Sep 2024 09:36:46 -0400 Subject: [PATCH] fix UI keycloak var, gpu_runtime --- Makefile | 4 ++-- bundles/dev/cpu/uds-config.yaml | 4 ++-- bundles/dev/gpu/uds-config.yaml | 4 ++-- bundles/latest/cpu/uds-config.yaml | 4 ++-- bundles/latest/gpu/uds-config.yaml | 4 ++-- packages/text-embeddings/zarf.yaml | 2 +- packages/ui/values/upstream-values.yaml | 2 +- packages/ui/zarf.yaml | 2 +- packages/vllm/zarf.yaml | 2 +- packages/whisper/zarf.yaml | 2 +- 10 files changed, 15 insertions(+), 15 deletions(-) diff --git a/Makefile b/Makefile index b9ba43e4e..c1426210e 100644 --- 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 index 2c2dfbd9d..19cd00027 100644 --- 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 index 0d39b2632..9ad6cfdb4 100644 --- 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 index 3e0ccb54a..5caff096b 100644 --- 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 index 0d39b2632..9ad6cfdb4 100644 --- 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 index 563d507b4..a413b53c9 100644 --- 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)?$" diff --git a/packages/ui/values/upstream-values.yaml b/packages/ui/values/upstream-values.yaml index 46bd6fbf5..fa2296f0a 100644 --- a/packages/ui/values/upstream-values.yaml +++ b/packages/ui/values/upstream-values.yaml @@ -18,7 +18,7 @@ env: - name: PUBLIC_SUPABASE_URL value: "https://supabase-kong.###ZARF_VAR_DOMAIN###" - name: PUBLIC_DISABLE_KEYCLOAK - value: "true" + value: "###ZARF_VAR_DISABLE_KEYCLOAK###" - name: PUBLIC_MESSAGE_LENGTH_LIMIT value: "10000" - name: SUPABASE_AUTH_EXTERNAL_KEYCLOAK_URL diff --git a/packages/ui/zarf.yaml b/packages/ui/zarf.yaml index 933985f50..3924beef5 100644 --- a/packages/ui/zarf.yaml +++ b/packages/ui/zarf.yaml @@ -16,7 +16,7 @@ variables: prompt: true sensitive: true - name: OPENAI_API_KEY - description: OpenAI API Key. If specified, app will use OpenAI instead of LeapfrogAI + description: OpenAI API key - if specified, the UI will use OpenAI instead of LeapfrogAI prompt: true default: "" sensitive: true diff --git a/packages/vllm/zarf.yaml b/packages/vllm/zarf.yaml index 881cb1e09..e31a79c0d 100644 --- a/packages/vllm/zarf.yaml +++ b/packages/vllm/zarf.yaml @@ -15,7 +15,7 @@ variables: description: The GPU limit for the model inferencing. Must be 1 or more. default: "1" pattern: "^[1-9][0-9]*$" - - name: GPU_RUNTIME_NAME + - name: GPU_RUNTIME description: The GPU runtime name for the model inferencing. default: "nvidia" pattern: "^(nvidia)?$" diff --git a/packages/whisper/zarf.yaml b/packages/whisper/zarf.yaml index 7bd134553..475bb8275 100644 --- a/packages/whisper/zarf.yaml +++ b/packages/whisper/zarf.yaml @@ -16,7 +16,7 @@ variables: description: The GPU limit for the model inferencing. default: "0" pattern: "^[0-9]+$" - - name: GPU_RUNTIME_NAME + - name: GPU_RUNTIME description: The GPU runtime name for the model inferencing. Leave blank for CPU-only. default: "" pattern: "^(nvidia)?$"