Rohan PotdarandElizaWszola a51376b3f0 [Performance][DSR1]: Fused RoPE+KVCache+q_concat for MLA (#40392) ...

Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>

2026-05-11 14:10:50 +00:00

..

__init__.py

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

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

fix_functionalization.py

[Performance][DSR1]: Fused RoPE+KVCache+q_concat for MLA (#40392)

2026-05-11 14:10:50 +00:00

noop_elimination.py

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

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

post_cleanup.py

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

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

scatter_split_replace.py

[ROCm]: Enable customop and rope+kvcache fusion for AITER RoPE (#35180)

2026-02-25 04:36:40 +00:00

split_coalescing.py

[Bugfix] Fix QK Norm+RoPE fusion pattern matching on B200+FP8 (#33967)

2026-02-07 02:27:33 +00:00