Skip to content

GitLab

Unverified Commit eeab52a4 authored by Zhuohan Li's avatar Zhuohan Li Committed by GitHub
Browse files

[FIX] Simpler fix for async engine running on ray (#3371)

parent c33afd89
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 2 deletions
vllm/executor/ray_gpu_executor.py
View file @ eeab52a4
...@@ -430,8 +430,7 @@ class RayGPUExecutorAsync(RayGPUExecutor, ExecutorAsyncBase): ...@@ -430,8 +430,7 @@ class RayGPUExecutorAsync(RayGPUExecutor, ExecutorAsyncBase):
"blocks_to_swap_in": blocks_to_swap_in, "blocks_to_swap_in": blocks_to_swap_in,
"blocks_to_swap_out": blocks_to_swap_out, "blocks_to_swap_out": blocks_to_swap_out,
"blocks_to_copy": blocks_to_copy, "blocks_to_copy": blocks_to_copy,
}, })
use_ray_compiled_dag=USE_RAY_COMPILED_DAG)
# Only the driver worker returns the sampling results. # Only the driver worker returns the sampling results.
output = all_outputs[0] output = all_outputs[0]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment