phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 06:12:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-watsonx-inference-adapter

Browse source
This commit is contained in:
Sajikumar JS 2025-04-07 10:42:30 +05:30
commit 5366c423ae
10 changed files with 1355 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

9
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,
@ -338,6 +341,9 @@ class MetaReferenceInferenceImpl(
stop_reason = None
for token_result in self.generator.chat_completion(request):
if os.environ.get("LLAMA_MODELS_DEBUG", "0") == "1":
cprint(token_result.text, "cyan", end="")
tokens.append(token_result.token)
if token_result.token == tokenizer.eot_id:
@ -386,6 +392,9 @@ class MetaReferenceInferenceImpl(
ipython = False
for token_result in self.generator.chat_completion(request):
if os.environ.get("LLAMA_MODELS_DEBUG", "0") == "1":
cprint(token_result.text, "cyan", end="")
tokens.append(token_result.token)
if not ipython and token_result.text.startswith("<|python_tag|>"):