updated code for workflow issues

llama_stack/providers/remote/inference/watsonx/models.py

@@ -40,10 +40,6 @@ MODEL_ENTRIES = [
         "meta-llama/llama-3-2-90b-vision-instruct",
         CoreModelId.llama3_2_90b_vision_instruct.value,
     ),
-    # build_hf_repo_model_entry(
-    #     "meta-llama/llama-3-405b-instruct",
-    #     CoreModelId.llama3_405b_instruct.value,
-    # ),
     build_hf_repo_model_entry(
         "meta-llama/llama-guard-3-11b-vision",
         CoreModelId.llama_guard_3_11b_vision.value,

llama_stack/providers/remote/inference/watsonx/watsonx.py

@@ -7,7 +7,6 @@
 from typing import AsyncGenerator, List, Optional, Union
 
 from llama_stack.apis.common.content_types import InterleavedContent, InterleavedContentItem
-from llama_stack.models.llama.datatypes import SamplingParams, ToolDefinition, ToolPromptFormat
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
 from llama_stack.apis.inference import (
     ChatCompletionRequest,
@@ -30,8 +29,6 @@ from llama_stack.apis.inference import (
 from llama_stack.providers.utils.inference.openai_compat import (
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,
-    convert_message_to_openai_dict,
-    get_sampling_options,
     process_chat_completion_response,
     process_chat_completion_stream_response,
     process_completion_response,

llama_stack/templates/watsonx/doc_template.md

@@ -68,6 +68,6 @@ docker run \
 llama stack build --template watsonx --image-type conda
 llama stack run ./run.yaml \
   --port $LLAMA_STACK_PORT \
-  --env WATSONX_API_KEY=$WATSONX_API_KEY  \
+  --env WATSONX_API_KEY=$WATSONX_API_KEY \
   --env WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID
 ```