feat(gemma4): add E-series tensor parallelism (#3512)

* feat(gemma4): add E-series tensor parallelism

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>

* chore(gemma4): remove mock TP parity recipe

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>

* perf(gemma4): default E4B recipe to TP2 CP2

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>

* fix(ci): add Gemma4 recipe owner

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>

* refactor(gemma4): delegate E-series mask preparation

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>

* chore(gemma4): name E4B recipe for TP2 CP2

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>

---------

Signed-off-by: HuiyingLi <willwin.lee@gmail.com>