use free_table as a mask tensor

[sywangyi]

What does this PR do?

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[sywangyi]

in MAX1550
for beam=4, 1024in/256out see 3%improvement in TPOT
for beam=1 1024in/256out. see 2%impovement in TTFT