vllm/tests/compile/piecewise at e6cdbd6792eb3a33f41963a1f1ea4e6314d4a27c - vllm

Files

Morrison Turnansky e3fdb627d9 [FrontEnd] UNREVERT CompilationConfig overhaul (#20283 ): deprecate use_inductor in favor of backend, simplify custom_ops (#26502 )

Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2025-10-13 22:47:16 +00:00

__init__.py

[torch.compile] rework compile control with piecewise cudagraph (#9715 )

2024-10-29 23:03:49 -07:00

test_full_cudagraph.py

[V0 Deprecation] Remove VLLM_USE_V1 from tests (#26341 )

2025-10-07 15:42:31 +00:00

test_multiple_graphs.py

[torch.compile] Make inductor partition rules respect splitting_ops #25691 (#25845 )

2025-10-10 16:35:28 +00:00

test_simple.py

[torch.compile] Make inductor partition rules respect splitting_ops #25691 (#25845 )

2025-10-10 16:35:28 +00:00

test_toy_llama.py

[FrontEnd] UNREVERT CompilationConfig overhaul (#20283 ): deprecate use_inductor in favor of backend, simplify custom_ops (#26502 )

2025-10-13 22:47:16 +00:00