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

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): Set up -O infrastructure (#26847)

Browse Source 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: adabeyta <aabeyta@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: adabeyta <aabeyta@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Morrison Turnansky
2025-11-27 04:55:58 -05:00
committed by GitHub
parent 00d3310d2d
commit 0838b52e2e
13 changed files with 735 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/compile/test_config.py
View File

@@ -172,8 +172,8 @@ def test_splitting_ops_dynamic():
config = VllmConfig()
# Default V1 config leaves cudagraph mode unset; splitting ops are only
# populated when the engine decides to use piecewise compilation.
assert config.compilation_config.cudagraph_mode == CUDAGraphMode.NONE
assert not config.compilation_config.splitting_ops_contain_attention()
assert config.compilation_config.cudagraph_mode == CUDAGraphMode.FULL_AND_PIECEWISE
assert config.compilation_config.splitting_ops_contain_attention()
# When use_inductor_graph_partition=True
config = VllmConfig(