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

[torch.compile] Significantly speed up cold start times (#33641)

Browse Source 
Signed-off-by: Richard Zou <zou3519@gmail.com>
This commit is contained in:
Richard Zou
2026-02-03 09:12:11 -08:00
committed by GitHub
parent 2267cb1cfd
commit b1bb18de8d
3 changed files with 41 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/compilation/compiler_interface.py
View File

@@ -101,7 +101,6 @@ class CompilerInterface:
handle: Any,
graph: fx.GraphModule,
example_inputs: list[Any],
graph_index: int,
compile_range: Range,
) -> Callable[..., Any]:
"""
@@ -302,7 +301,6 @@ class InductorStandaloneAdaptor(CompilerInterface):
handle: Any,
graph: fx.GraphModule,
example_inputs: list[Any],
graph_index: int,
compile_range: Range,
) -> Callable[..., Any]:
assert isinstance(handle, tuple)
@@ -527,7 +525,6 @@ class InductorAdaptor(CompilerInterface):
handle: Any,
graph: fx.GraphModule,
example_inputs: list[Any],
graph_index: int,
compile_range: Range,
) -> Callable[..., Any]:
assert isinstance(handle, tuple)