phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-21 04:02:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into pr2940

Browse source
This commit is contained in:
Ashwin Bharambe 2025-08-21 18:19:43 -07:00 • committed by GitHub
commit 760295af50
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
229 changed files with 17933 additions and 7872 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/inference/meta_reference/parallel_utils.py
View file

@ -12,7 +12,6 @@
import copy
import json
import logging
import multiprocessing
import os
import tempfile
@ -32,13 +31,14 @@ from fairscale.nn.model_parallel.initialize import (
from pydantic import BaseModel, Field
from torch.distributed.launcher.api import LaunchConfig, elastic_launch
from llama_stack.log import get_logger
from llama_stack.models.llama.datatypes import GenerationResult
from llama_stack.providers.utils.inference.prompt_adapter import (
ChatCompletionRequestWithRawContent,
CompletionRequestWithRawContent,
)
log = logging.getLogger(__name__)
log = get_logger(name=__name__, category="inference")
class ProcessingMessageName(str, Enum):