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

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

@ -11,7 +11,7 @@ import tempfile
import time
import uuid
from enum import Enum
from typing import Any, Callable, Generator, List, Literal, Optional, Union
from typing import Callable, Generator, List, Literal, Optional, Union
import torch
@ -317,7 +317,7 @@ def start_model_parallel_process(
request_socket.send(encode_msg(ReadyRequest()))
response = request_socket.recv()
print(f"Finished model load {response}")
print("Loaded model...")
return request_socket, process