xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-19 00:57:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: include prefill_context_parallel_size in world_size breakdown

Browse Source 
Address review feedback: the world_size calculation includes
prefill_context_parallel_size, so include it in the breakdown
when it's > 1 to make the message fully accurate.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Signed-off-by: yurekami <yurekami@users.noreply.github.com>
This commit is contained in:
yurekami 2025-12-25 03:26:53 +09:00
parent 9380f13f5b
commit 0ec051a4c8
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/v1/executor/ray_utils.py
View File

@ -334,12 +334,15 @@ def initialize_ray_cluster(
"placement group allocation failures. For multi-node Ray "
"clusters, ensure your cluster has %d GPUs available across "
"all nodes. (world_size = tensor_parallel_size=%d × "
"pipeline_parallel_size=%d)",
"pipeline_parallel_size=%d%s)",
parallel_config.world_size,
available_gpus,
parallel_config.world_size,
parallel_config.tensor_parallel_size,
parallel_config.pipeline_parallel_size,
(f" × prefill_context_parallel_size="
f"{parallel_config.prefill_context_parallel_size}"
if parallel_config.prefill_context_parallel_size > 1 else ""),
)
if ray.is_initialized():