Merge branch 'main' into enable-vector-stores-files-api-tests

docs/source/apis/external.md

@@ -355,7 +355,7 @@ server:
 8. Run the server:
 
 ```bash
-python -m llama_stack.distribution.server.server --yaml-config ~/.llama/run-byoa.yaml
+python -m llama_stack.core.server.server --yaml-config ~/.llama/run-byoa.yaml
 ```
 
 9. Test the API:

docs/source/building_applications/playground/index.md

@@ -103,5 +103,5 @@ llama stack run together
 
 2. Start Streamlit UI
 ```bash
-uv run --with ".[ui]" streamlit run llama_stack/distribution/ui/app.py
+uv run --with ".[ui]" streamlit run llama_stack.core/ui/app.py
 ```

docs/source/deploying/kubernetes_deployment.md

@@ -174,7 +174,7 @@ spec:
       - name: llama-stack
         image: localhost/llama-stack-run-k8s:latest
         imagePullPolicy: IfNotPresent
-        command: ["python", "-m", "llama_stack.distribution.server.server", "--config", "/app/config.yaml"]
+        command: ["python", "-m", "llama_stack.core.server.server", "--config", "/app/config.yaml"]
         ports:
           - containerPort: 5000
         volumeMounts:

docs/source/distributions/building_distro.md

@@ -59,7 +59,7 @@ Build a Llama stack container
 
 options:
   -h, --help            show this help message and exit
-  --config CONFIG       Path to a config file to use for the build. You can find example configs in llama_stack/distributions/**/build.yaml. If this argument is not provided, you will
+  --config CONFIG       Path to a config file to use for the build. You can find example configs in llama_stack.cores/**/build.yaml. If this argument is not provided, you will
                         be prompted to enter information interactively (default: None)
   --template TEMPLATE   Name of the example template config to use for build. You may use `llama stack build --list-templates` to check out the available templates (default: None)
   --list-templates      Show the available templates for building a Llama Stack distribution (default: False)

docs/source/distributions/importing_as_library.md

@@ -10,7 +10,7 @@ llama stack build --template starter --image-type venv
 ```
 
 ```python
-from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 client = LlamaStackAsLibraryClient(
     "starter",

docs/source/distributions/k8s/stack-k8s.yaml.template

@@ -52,7 +52,7 @@ spec:
           value: "${SAFETY_MODEL}"
         - name: TAVILY_SEARCH_API_KEY
           value: "${TAVILY_SEARCH_API_KEY}"
-        command: ["python", "-m", "llama_stack.distribution.server.server", "--config", "/etc/config/stack_run_config.yaml", "--port", "8321"]
+        command: ["python", "-m", "llama_stack.core.server.server", "--config", "/etc/config/stack_run_config.yaml", "--port", "8321"]
         ports:
           - containerPort: 8321
         volumeMounts:

docs/source/providers/post_training/inline_huggingface.md

@@ -24,6 +24,10 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
 | `weight_decay` | `<class 'float'>` | No | 0.01 |  |
 | `dataloader_num_workers` | `<class 'int'>` | No | 4 |  |
 | `dataloader_pin_memory` | `<class 'bool'>` | No | True |  |
+| `dpo_beta` | `<class 'float'>` | No | 0.1 |  |
+| `use_reference_model` | `<class 'bool'>` | No | True |  |
+| `dpo_loss_type` | `Literal['sigmoid', 'hinge', 'ipo', 'kto_pair'` | No | sigmoid |  |
+| `dpo_output_dir` | `<class 'str'>` | No | ./checkpoints/dpo |  |
 
 ## Sample Configuration