xla
[Kernel] support kv cache quantization in ragged attention kernel
#9249

Merged

[Kernel] support kv cache quantization in ragged attention kernel #9249

qihqi merged 6 commits into master from chengji/improve-attn

[Kernel] support kv cache quantization in ragged attention kernel

b57e4578

yaochengji requested a review from

vanbasten23 318 days ago

modify python op

d3655f89

fix test

52a00099

yaochengji force pushed from 057c40b0 to 52a00099 318 days ago

fix test

5749e4c6

fix test

070138a4

yaochengji force pushed from cfee66b5 to 070138a4 318 days ago

vanbasten23 commented on 2025-05-28

fix comments

80412afe

vanbasten23 approved these changes on 2025-05-29

qihqi merged 2edcd2e3 into master 316 days ago

Reviewers

vanbasten23

Assignees

No one assigned

Labels

None yet

Milestone

No milestone