phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 19:30:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

final fixes

Browse source
This commit is contained in:
Hardik Shah 2025-04-06 18:01:43 -07:00
parent 971566fd74
commit d3ebc18559
3 changed files with 11 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -6,8 +6,11 @@
import asyncio
import logging
import os
from typing import AsyncGenerator, List, Optional, Union
from termcolor import cprint
from llama_stack.apis.common.content_types import (
TextDelta,
ToolCallDelta,
@ -338,9 +341,8 @@ class MetaReferenceInferenceImpl(
stop_reason = None
for token_result in self.generator.chat_completion(request):
from termcolor import cprint
cprint(token_result.text, "cyan", end="")
if os.environ.get("LLAMA_MODELS_DEBUG", "0") == "1":
cprint(token_result.text, "cyan", end="")
tokens.append(token_result.token)
@ -390,9 +392,8 @@ class MetaReferenceInferenceImpl(
ipython = False
for token_result in self.generator.chat_completion(request):
from termcolor import cprint
cprint(token_result.text, "cyan", end="")
if os.environ.get("LLAMA_MODELS_DEBUG", "0") == "1":
cprint(token_result.text, "cyan", end="")
tokens.append(token_result.token)