phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 02:58:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix vllm bugs

Browse source
This commit is contained in:
Hardik Shah 2025-03-18 13:57:36 -07:00
parent 549096b264
commit b0425c84b5
1 changed files with 3 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -89,16 +89,12 @@ def _convert_to_vllm_tool_calls_in_response(
if not tool_calls: if not tool_calls:
return [] return []
call_function_arguments = None
for call in tool_calls:
call_function_arguments = json.loads(call.function.arguments)
return [ return [
ToolCall( ToolCall(
call_id=call.id, call_id=call.id,
tool_name=call.function.name, tool_name=call.function.name,
arguments=json.loads(call.function.arguments), arguments=json.loads(call.function.arguments),
arguments_json=call_function_arguments, arguments_json=call.function.arguments,
) )
for call in tool_calls for call in tool_calls
] ]
@ -182,7 +178,8 @@ async def _process_vllm_chat_completion_stream_response(
tool_call=ToolCall( tool_call=ToolCall(
call_id=tool_call_buf.call_id, call_id=tool_call_buf.call_id,
tool_name=tool_call_buf.tool_name, tool_name=tool_call_buf.tool_name,
arguments=args_str, arguments=args,
arguments_json=args_str,
), ),
parse_status=ToolCallParseStatus.succeeded, parse_status=ToolCallParseStatus.succeeded,
), ),