Luka Govedič bd56c983d6 [torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902) ...

Signed-off-by: luka <luka@neuralmagic.com>

2025-02-28 16:20:11 -07:00

..

piecewise

[torch.compile] PyTorch 2.6 and nightly compatibility (#12393)

2025-02-07 01:09:07 +08:00

__init__.py

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

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

backend.py

[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902)

2025-02-28 16:20:11 -07:00

test_basic_correctness.py

Consolidate Llama model usage in tests (#13094)

2025-02-13 22:18:03 -08:00

test_full_graph.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

test_functionalization.py

[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902)

2025-02-28 16:20:11 -07:00

test_fusion.py

[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902)

2025-02-28 16:20:11 -07:00

test_pass_manager.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

test_wrapper.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

utils.py

Consolidate Llama model usage in tests (#13094)

2025-02-13 22:18:03 -08:00