chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

refactor: extract device-to-backend mapping into get_default_distributed_backend (#19202)

Browse Source 
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
This commit is contained in:
Wang, Yi
2026-02-25 15:50:26 +08:00
committed by GitHub
parent d0bb140034
commit 3d879c69e9
3 changed files with 27 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/disaggregation/encode_server.py
View File

@@ -25,6 +25,7 @@ from sglang.srt.configs.load_config import LoadConfig
from sglang.srt.configs.model_config import ModelConfig
from sglang.srt.disaggregation.encode_receiver import EmbeddingData
from sglang.srt.distributed.parallel_state import (
get_default_distributed_backend,
get_mooncake_transfer_engine,
get_tp_group,
init_distributed_environment,
@@ -176,6 +177,7 @@ class MMEncoder:
self.use_image_processor_gpu = use_image_processor_gpu
init_distributed_environment(
backend=get_default_distributed_backend(self.device),
world_size=server_args.tp_size,
rank=rank,
distributed_init_method=dist_init_method,