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

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change compilation level to compilation mode, deprecation compilation level (#26355)

Browse Source 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Morrison Turnansky
2025-10-14 22:51:16 -04:00
committed by GitHub
parent e66d787bce
commit 96b9aa5aa0
42 changed files with 270 additions and 248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/compilation/compiler_interface.py
View File

@@ -575,7 +575,7 @@ class InductorAdaptor(CompilerInterface):
Because it is re-entrant, we always set it (even if entering via Dynamo
and the context was already entered). We might want to revisit if it
should be set at a different level of compilation.
should be set at a different mode of compilation.
This is likely a bug in PyTorch: public APIs should not rely on
manually setting up internal contexts. But we also rely on non-public