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

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/getting_started/installation/gpu/xpu.inc.md
View File

@@ -81,4 +81,9 @@ python -m vllm.entrypoints.openai.api_server \
By default, a ray instance will be launched automatically if no existing one is detected in the system, with `num-gpus` equals to `parallel_config.world_size`. We recommend properly starting a ray cluster before execution, referring to the <gh-file:examples/online_serving/run_cluster.sh> helper script.
# --8<-- [end:supported-features]
# --8<-- [start:distributed-backend]
XPU platform uses **torch-ccl** for torch<2.8 and **xccl** for torch>=2.8 as distributed backend, since torch 2.8 supports **xccl** as built-in backend for XPU.
# --8<-- [end:distributed-backend]
# --8<-- [end:extra-information]