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

Use standalone_compile by default in torch >= 2.8.0 (#18846)

Browse Source 
Signed-off-by: rzou <zou3519@gmail.com>
This commit is contained in:
Richard Zou
2025-05-29 18:41:58 -04:00
committed by GitHub
parent 64eaf5fe05
commit a521ef06e5
3 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/compilation/compiler_interface.py
View File

@@ -155,7 +155,7 @@ class InductorStandaloneAdaptor(CompilerInterface):
This is not on by default yet, but we plan to turn it on by default for
PyTorch 2.8.
Use VLLM_TEST_STANDALONE_COMPILE to toggle this on or off.
Use VLLM_USE_STANDALONE_COMPILE to toggle this on or off.
"""
name = "inductor_standalone"