phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Split off meta-reference-quantized provider

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-10 15:54:08 -07:00
parent 7ff5800dea
commit 1ff0476002
10 changed files with 54 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/cli/stack/build.py
View file

@ -149,6 +149,7 @@ class StackBuild(Subcommand):
def _run_template_list_cmd(self, args: argparse.Namespace) -> None:
import json
from llama_stack.cli.table import print_table
# eventually, this should query a registry at llama.meta.com/llamastack/distributions
@ -175,6 +176,7 @@ class StackBuild(Subcommand):
def _run_stack_build_command(self, args: argparse.Namespace) -> None:
import textwrap
import yaml
from llama_stack.distribution.distribution import get_provider_registry
from prompt_toolkit import prompt
@ -256,7 +258,9 @@ class StackBuild(Subcommand):
providers = dict()
for api, providers_for_api in get_provider_registry().items():
available_providers = [
x for x in providers_for_api.keys() if x != "remote"
x
for x in providers_for_api.keys()
if x not in ("remote", "remote::sample")
]
api_provider = prompt(
"> Enter provider for API {}: ".format(api.value),