[Refactor] Remove redundant attention operator branches.#4531

Merged

weijinqian0 merged 19 commits intovllm-project:mainfrom

weijinqian0:refactor_attention_main

Dec 2, 2025

Commits on Nov 28, 2025

[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed
[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed

Commits on Nov 29, 2025

[Refactor] add fia_v3 attention & remove other attention operator.
weijinqian_v1
committed

Commits on Dec 1, 2025

[bugfix] Repair the problem of moe model accuracy caused by version upgrade.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed
[Refactor] extract attention cp.
weijinqian_v1
committed