phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 10:42:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

avoid tensor memory error

Browse source
This commit is contained in:
Yang Yang 2025-03-18 15:29:13 -07:00
parent 9c8e88ea9c
commit 5acbe76ed7
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/inline/inference/meta_reference/parallel_utils.py
View file

@ -10,6 +10,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import copy
import json
import logging
import multiprocessing
@ -213,7 +214,7 @@ def maybe_parse_message(maybe_json: Optional[str]) -> Optional[ProcessingMessage
def parse_message(json_str: str) -> ProcessingMessage:
data = json.loads(json_str)
return ProcessingMessageWrapper(**data).payload
return copy.deepcopy(ProcessingMessageWrapper(**data).payload)
def worker_process_entrypoint(