biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[1/N] Elastic EP Milestone 2 (#34861)

Browse Source 
Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
This commit is contained in:
Itay Alroy
2026-02-28 06:46:42 +02:00
committed by GitHub
parent 90805ff464
commit dea268336f
53 changed files with 3613 additions and 1016 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/lora/test_worker.py
View File

@@ -13,6 +13,7 @@ from vllm.config import (
ParallelConfig,
SchedulerConfig,
VllmConfig,
set_current_vllm_config,
)
from vllm.config.load import LoadConfig
from vllm.config.lora import LoRAConfig
@@ -77,8 +78,9 @@ def test_worker_apply_lora(qwen3_lora_files):
distributed_init_method=f"file://{tempfile.mkstemp()[1]}",
)
worker.init_device()
worker.load_model()
with set_current_vllm_config(vllm_config):
worker.init_device()
worker.load_model()
set_active_loras(worker, [])
assert worker.list_loras() == set()