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

5
tests/lora/test_fused_moe_lora_kernel.py
View File

@@ -6,7 +6,7 @@ import random
import pytest
import torch
from tests.utils import multi_gpu_test
from tests.utils import ensure_current_vllm_config, multi_gpu_test
from vllm import _custom_ops as ops
from vllm.distributed import (
init_distributed_environment,
@@ -631,7 +631,8 @@ def use_fused_moe_lora_kernel_tensor_parallel(
local_rank=local_rank,
distributed_init_method=init_method,
)
initialize_model_parallel(world_size, 1)
with ensure_current_vllm_config():
initialize_model_parallel(world_size, 1)
tp_size = get_tensor_model_parallel_world_size()
input_dim = K if column_parallel else N