|
295132c4a5
|
[NPU] Add sparsity-driven KV offload for DeepSeek DSA on Ascend (#33089)
Co-authored-by: itcj <itcj@foxmail.com>
Co-authored-by: chenyh <chenyh18@mail.ustc.edu.cn>
Co-authored-by: hibikid <7514545+hibikid@user.noreply.gitee.com>
Co-authored-by: Chengjie Tang <tangcj@sxu.edu.cn>
Co-authored-by: wangbiao0814 <wangbiao0814@outlook.com>
|
2026-09-09 09:13:22 +08:00 |
|