wip: test in CI

stackhpc · Feb 14, 2025 · 4ad5c11 · 4ad5c11
1 parent 2ee6354
commit 4ad5c11
Show file tree

Hide file tree

Showing 3 changed files with 1 addition and 24 deletions.
diff --git a/charts/azimuth-chat/ci/ui-only-values.yaml b/charts/azimuth-chat/ci/ui-only-values.yaml
diff --git a/charts/azimuth-llm/values.yaml b/charts/azimuth-llm/values.yaml
@@ -56,8 +56,7 @@ api:
     hostPath:
       path: /tmp/llm/huggingface-cache
   # Number of gpus to requests for each api pod instance
-  # NOTE: This must be in the range 1 <= value <= N, where
-  # 'N' is the number of GPUs available in a single
+  # NOTE: This must be less than the number of GPUs available in a single
   # worker node on the target Kubernetes cluster.
   # NOTE: According to the vLLM docs found here
   # https://docs.vllm.ai/en/latest/serving/distributed_serving.html

diff --git a/web-apps/chat/defaults.yml b/web-apps/chat/defaults.yml
@@ -1,9 +1,3 @@
-
-# Default target is a local ollama instance
-# running inside the same docker network
-model_name: smollm2:135m
-backend_url: http://ollama:11434
-
 host_address: 0.0.0.0
 
 model_instruction: "You are a helpful and cheerful AI assistant. Please respond appropriately."