mirror of
https://github.com/deepspeedai/DeepSpeed.git
synced 2025-10-21 16:48:52 +08:00
- FastPersist - ZeRO-Inference+SGLang --------- Signed-off-by: Olatunji Ruwase <olruwase@microsoft.com> Signed-off-by: Olatunji Ruwase <tunji.ruwase@snowflake.com> Co-authored-by: jerryyangli <jerryyangli@gmail.com> Co-authored-by: Yang Li <yangli2@microsoft.com> Co-authored-by: Guanhua Wang <alexwgh333@gmail.com> Co-authored-by: Connor Holmes <connorholmes@microsoft.com> Co-authored-by: Bing Xie <67908712+xiexbing@users.noreply.github.com> Co-authored-by: cassieesvelt <73311224+cassieesvelt@users.noreply.github.com> Co-authored-by: Jeff Rasley <jerasley@microsoft.com> Co-authored-by: Logan Adams <114770087+loadams@users.noreply.github.com> Co-authored-by: Michael Wyatt <michaelwyatt@microsoft.com> Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com> Co-authored-by: swli <47371259+lucasleesw@users.noreply.github.com> Co-authored-by: Cheng Li <pistasable@gmail.com> Co-authored-by: Molly Smith <112220543+molly-smith@users.noreply.github.com> Co-authored-by: Ubuntu <jomayeri@microsoft.com> Co-authored-by: Olatunji Ruwase <tunji.ruwase@snowflake.com> Co-authored-by: Zhipeng Wang <zhipeng.rainbowserie@gmail.com>
26 lines
867 B
Python
26 lines
867 B
Python
# Copyright (c) Microsoft Corporation.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
# DeepSpeed Team
|
|
|
|
import os
|
|
from datetime import timedelta
|
|
|
|
#############################################
|
|
# Torch distributed constants
|
|
#############################################
|
|
TORCH_DISTRIBUTED_DEFAULT_PORT = 29500
|
|
|
|
# Default process group wide timeout, if applicable.
|
|
# This only applies to the gloo and nccl backends
|
|
# (only if NCCL_BLOCKING_WAIT or NCCL_ASYNC_ERROR_HANDLING is set to 1).
|
|
# To make an attempt at backwards compatibility with THD, we use an
|
|
# extraordinarily high default timeout, given that THD did not have timeouts.
|
|
default_pg_timeout = timedelta(minutes=int(os.getenv("DEEPSPEED_TIMEOUT", default=30)))
|
|
INFERENCE_GENERIC_MODE = 'generic'
|
|
INFERENCE_SPECIALIZED_MODE = 'specialized'
|
|
|
|
CROSS_RANK = "CROSS_RANK"
|
|
CROSS_SIZE = "CROSS_SIZE"
|
|
LOCAL_RANK = 'LOCAL_RANK'
|