xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-03 14:04:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Zhuohan Li 2024-03-13 14:18:40 -07:00 committed by GitHub
parent c33afd89f5
commit eeab52a4ff
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/executor/ray_gpu_executor.py
View File

@ -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]