Files

Luka Govedič 2915268369 [fix][torch.compile] Fix cold-start compilation time increase by adding kv cache update to splitting ops (#33441 )

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Richard Zou <zou3519@gmail.com>
(cherry picked from commit 15f40b20aa)

2026-02-02 00:14:07 -08:00

distributed

[Bugfix] Disable tma_aligned_scales in test_fusions_e2e (#32916 )

2026-01-23 14:34:30 +00:00

fullgraph

[Misc][LLaMa4] Compile LLaMa Vision Encoder (#30709 )

2026-01-09 22:01:38 -05:00

__init__.py

[torch.compile] register allreduce operations as custom ops (#8526 )

2024-09-16 22:57:57 -07:00

backend.py

[torch.compile] Enable attention and allreduce fusion without custom ops enabled (#24604 )

2025-10-17 08:10:23 -06:00

fusion_test_utils.py

[CI] Breakup h200 tests (#30499 )

2026-01-16 06:23:22 +00:00

README.md

[CI] Reorganize compile tests so new tests are automatically included in CI (#28625 )

2025-11-19 06:13:50 -08:00

silly_attention.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908 )

2025-10-18 09:48:22 -07:00

test_aot_compile.py

[AOT compilation] support torch.compile inductor artifacts in VllmCompiledFunction (#25205 )

2026-01-20 19:45:59 +00:00

test_cold_start.py

[fix][torch.compile] Fix cold-start compilation time increase by adding kv cache update to splitting ops (#33441 )

2026-02-02 00:14:07 -08:00

test_compile_ranges.py

[BugFix] Fix non detected failing tests (#30277 )

2025-12-09 17:57:55 +00:00

test_config.py

[Misc] Remove pad_for_cudagraphs from config (#30143 )

2026-01-20 15:05:48 -05:00

test_decorator.py

Remove deprecated fields from CompilationConfig (#27593 )

2025-11-12 16:10:28 +00:00

test_dynamic_shapes_compilation.py

[ci] Fix Pytorch compilation test oom in 2.10 (#31194 )

2025-12-23 01:56:47 +00:00

test_functionalization.py

[Refactor] Make FP8 Linear Ops use kernel abstraction (#27814 )

2026-01-20 14:48:20 +08:00

test_fusion_attn.py

[torch.compile][CI] Add back attn fusion on hopper/ada (#32940 )

2026-01-23 16:49:20 +00:00

test_fusion.py

[Refactor] Make FP8 Linear Ops use kernel abstraction (#27814 )

2026-01-20 14:48:20 +08:00

test_graph_partition.py

[fix][torch.compile] Fix cold-start compilation time increase by adding kv cache update to splitting ops (#33441 )

2026-02-02 00:14:07 -08:00

test_noop_elimination.py

[ROCm][CI] Fix tests/compile unit tests (#28895 )

2026-01-06 18:50:43 +00:00

test_pass_manager.py

[Misc][BE] Turn on strict type coverage for vllm/compilation (#31756 )

2026-01-22 15:12:26 +00:00

test_qk_norm_rope_fusion.py

[1/N][Attention] Restructure attention: move files (#31916 )

2026-01-09 13:10:24 -08:00

test_silu_mul_quant_fusion.py

[torch.compile] Compile CustomOp.forward_native for SiluAndMul and QuantFP8 to avoid raw torch ops inside opaque custom ops (#32806 )

2026-01-22 19:52:26 -08:00

test_wrapper.py

Avoid bytecode hook and simplify TorchCompileWrapperWithCustomDipatch (#25110 )

2025-11-14 14:11:10 -08:00

README.md

compile test folder structure

compile/test_*.py : various unit tests meant for testing particular code path/features. Future tests are most likely added here. New test files added here will be included in CI automatically
compile/fullgraph/ : full model tests, including all tests previously in compile/piecewise. These tests do not target particular features. New test files added here will be included in CI automatically
compile/distributed/ : tests that require multiple GPUs. New test files added here will NOT be included in CI automatically as these tests generally need to be manually configured to run in runners with particular number/type of GPUs.