3 people b715699df4 [ROCm][Perf] Extend QK-norm/RoPE/KV-cache fusion to MRoPE (#50212) ...

Signed-off-by: Vorapol Assavasangthong <Vorapol.Assavasangthong@amd.com>
Co-authored-by: Santosh Hiremath <Santosh.Hiremath@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>

2026-09-23 11:11:57 -05:00

..

__init__.py

[CI][torch.compile] Reduce e2e fusion test time (#33293)

2026-02-04 19:09:03 -05:00

common.py

[ROCm][Perf] Extend QK-norm/RoPE/KV-cache fusion to MRoPE (#50212)

2026-09-23 11:11:57 -05:00

conftest.py

[ROCm][Perf] Extend QK-norm/RoPE/KV-cache fusion to MRoPE (#50212)

2026-09-23 11:11:57 -05:00

models.py

[Model][NVIDIA] Route DSA models to the CUDA non-compiled path (#52861)

2026-08-19 00:13:52 -07:00

test_tp1_quant.py

[Fusion] Manual ActivationQuantFusionPass initial application (#51415)

2026-09-03 13:37:31 -04:00

test_tp2_ar_rms.py

[Fusion] Manual ActivationQuantFusionPass initial application (#51415)

2026-09-03 13:37:31 -04:00

test_tp2_async_tp.py

[Fusion] Manual ActivationQuantFusionPass initial application (#51415)

2026-09-03 13:37:31 -04:00

test_tp2_rocm_async_tp.py

[ROCm][Compile] Support BF16 AsyncTP fusion (#58098)

2026-09-22 20:36:38 -05:00