xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 16:15:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1][PP] Enable true PP with Ray executor (#13472)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-02-18 09:15:32 -08:00 committed by GitHub
parent a02c86b4dd
commit 4fb8142a0e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/executor/ray_distributed_executor.py
View File

@ -32,7 +32,7 @@ class RayDistributedExecutor(RayDistributedExecutorV0, Executor):
"""Ray distributed executor supports pipeline parallelism, """Ray distributed executor supports pipeline parallelism,
meaning that it allows PP size batches to be executed concurrently. meaning that it allows PP size batches to be executed concurrently.
""" """
return 1 #self.vllm_config.parallel_config.pipeline_parallel_size return self.parallel_config.pipeline_parallel_size
def execute_model( def execute_model(
self, self,