mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
30 lines
910 B
Python
30 lines
910 B
Python
import argparse
|
|
import textwrap
|
|
|
|
from toolchain.cli.inference.configure import InferenceConfigure
|
|
from toolchain.cli.inference.start import InferenceStart
|
|
from toolchain.cli.subcommand import Subcommand
|
|
|
|
|
|
class InferenceParser(Subcommand):
|
|
"""Llama cli for inference apis"""
|
|
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"inference",
|
|
prog="llama inference",
|
|
description="Run inference on a llama model",
|
|
epilog=textwrap.dedent(
|
|
"""
|
|
Example:
|
|
llama inference start <options>
|
|
"""
|
|
),
|
|
)
|
|
|
|
subparsers = self.parser.add_subparsers(title="inference_subcommands")
|
|
|
|
# Add sub-commandsa
|
|
InferenceStart.create(subparsers)
|
|
InferenceConfigure.create(subparsers)
|