Merge pull request lightspeed-core#452 from tisnik/lcore-599-bump-llama-stack-version-to-0.2.18

LCORE-599: bump-up Llama Stack version to 0.2.18

Author: tisnik

.github/workflows/e2e_tests.yaml

@@ -169,6 +169,7 @@ jobs:
                   checkpoint_format: huggingface
                   device: cpu
                   distributed_backend: null
+                  dpo_output_dir: '.'
                 provider_id: huggingface
                 provider_type: inline::huggingface
               safety:
@@ -262,4 +263,4 @@ jobs:
           uv sync
 
           echo "Running comprehensive e2e test suite..."
-          make test-e2e
+          make test-e2e

pyproject.toml

@@ -25,8 +25,8 @@ dependencies = [
     "fastapi>=0.115.12",
     "uvicorn>=0.34.3",
     "kubernetes>=30.1.0",
-    "llama-stack==0.2.17",
-    "llama-stack-client==0.2.17",
+    "llama-stack==0.2.18",
+    "llama-stack-client==0.2.18",
     "rich>=14.0.0",
     "cachetools>=6.1.0",
     "prometheus-client>=0.22.1",

run.yaml

@@ -69,6 +69,7 @@ providers:
       checkpoint_format: huggingface
       device: cpu
       distributed_backend: null
+      dpo_output_dir: "."
     provider_id: huggingface
     provider_type: inline::huggingface
   safety:

src/constants.py

@@ -2,7 +2,7 @@
 
 # Minimal and maximal supported Llama Stack version
 MINIMAL_SUPPORTED_LLAMA_STACK_VERSION = "0.2.17"
-MAXIMAL_SUPPORTED_LLAMA_STACK_VERSION = "0.2.17"
+MAXIMAL_SUPPORTED_LLAMA_STACK_VERSION = "0.2.18"
 
 UNABLE_TO_PROCESS_RESPONSE = "Unable to process this request"