iHore/vLLM

Fork 0

Files

T

History

MOVZXandHinata e61dcb9143

[Mini-vLLM] SM86-only cut: models, backends, Rust, tests

- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries
- Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels
- Remove inc/quark quant loaders; keep compressed-tensors and Marlin
- Drop the Rust frontend, pooling entrypoints, and idle test suites
- Rebuild kernels for sm_80;sm_86 and strip the extensions
- Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>

2026-10-18 19:19:56 +07:00

correctness_e2e

[CI][ROCm] Compare greedy output only in the AITER attn+quant test (#61185 )

2026-10-12 08:20:35 -05:00

dynamic_shapes

[CI] Split Dynamic Shapes out of (H200 MIG 35GB) PyTorch Compilation + (MI300) mirror (#58451 )

2026-09-28 00:32:11 -07:00

fullgraph

[CI][ROCm] Wait for VRAM to settle before building LLM in test_full_graph (#60872 )

2026-10-09 16:48:43 +00:00

fusions_e2e

[Compile] Remove torch.compile-based sequence parallelism and AsyncTP (#60517 )

2026-10-08 08:28:23 -07:00

h100

[CI][ROCm] Mirror remaining portable suites without duplicate coverage (#57877 )

2026-09-21 04:16:26 -05:00

passes

[ROCm] [fusion] support ROCm aiter fusion of per tensor quant + rmsnorm (#52831 )

2026-10-16 15:19:07 -05:00

__init__.py

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

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

backend.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

conftest.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +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

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

test_aot_compile.py

[Bugfix][Compile] Replace Transformers AOT caching with graph caching (#58918 )

2026-10-13 19:17:29 +00:00

test_codegen.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_compile_ranges.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_compiler_interface.py

[Bugfix][Compile] Replace Transformers AOT caching with graph caching (#58918 )

2026-10-13 19:17:29 +00:00

test_config.py

[Compile] Remove torch.compile-based sequence parallelism and AsyncTP (#60517 )

2026-10-08 08:28:23 -07:00

test_decorator.py

[Bugfix][CI] fix typos (#34934 )

2026-03-05 17:05:46 +00:00

test_graph_partition.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

test_inductor_fallback_allow_list_patch.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_rotary_embedding_compile.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901 )

2026-04-15 11:02:35 +08:00

test_structured_logging.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

test_wrapper.py

[MRV2] Support stock torch.compile mode (#59079 )

2026-09-28 20:17:48 -07:00

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.