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

7
tests/v1/worker/test_gpu_model_runner.py
View File

@@ -789,8 +789,11 @@ def test_hybrid_attention_mamba_tensor_shapes():
"MASTER_PORT": "12345",
}
)
init_distributed_environment()
initialize_model_parallel(tensor_model_parallel_size=1)
from tests.utils import ensure_current_vllm_config
with ensure_current_vllm_config():
init_distributed_environment()
initialize_model_parallel(tensor_model_parallel_size=1)
torch.set_default_dtype(torch.float16)
model_config = ModelConfig(