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

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

2026-02-06 04:19:49 -08:00

act_quant_fusion.py

Add pydocstyle to the ruff rules (#52136)

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

add_rms_fusion.py

[Compilation]Fuse Transformers Residual Add + RMSNorm (#48757)

2026-07-30 13:46:36 +00:00

allreduce_rms_fusion.py

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

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

attn_quant_fusion.py

[ROCm][Compile] Fuse AITER static FP8 attention output (#58099)

2026-09-23 03:16:52 -05:00

collective_fusion.py

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

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

matcher_utils.py

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

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

mla_attn_quant_fusion.py

Add pydocstyle to the ruff rules (#52136)

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

mla_rope_kvcache_cat_fusion.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

2026-09-12 00:36:47 -04:00

qk_norm_rope_fusion.py

Add pydocstyle to the ruff rules (#52136)

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

qk_norm_rope_kvcache_fusion.py

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

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

rms_quant_fusion.py

Add pydocstyle to the ruff rules (#52136)

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

rocm_aiter_fusion.py

[ROCm][Perf] Avoid extra reshape kernel in Qwen GDN output norm (#47842)

2026-09-22 14:38:16 +08:00

rope_kvcache_fusion.py

Add pydocstyle to the ruff rules (#52136)

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

sequence_parallelism.py

Add pydocstyle to the ruff rules (#52136)

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