[Refactor]Abstract Platform Interface for Distributed Backend and Add xccl Support for Intel XPU (#19410)

Signed-off-by: dbyoung18 <yang5.yang@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Yang Yang
2025-07-07 12:32:32 +08:00
committed by GitHub
parent 47db8c2c15
commit 6e2c19ce22
17 changed files with 44 additions and 8 deletions

View File

@@ -164,6 +164,7 @@ class RocmPlatform(Platform):
device_type: str = "cuda"
dispatch_key: str = "CUDA"
ray_device_key: str = "GPU"
dist_backend: str = "nccl"
# rocm shares the same device control env var as CUDA
device_control_env_var: str = "CUDA_VISIBLE_DEVICES"