Yuan Luoandluoyuan.luo 3340f4e3da [GDN][KDA][mem_cache] int8 checkpoint pool for the linear-attn prefix cache (#28185) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2026-06-17 20:41:46 -07:00

..

bench_cutedsl_kda_decode.py

[KDA] Fuse scaled_dot_kkt + solve_tril + recompute_w_u for KDA (#21604)

2026-03-31 20:57:27 -07:00

bench_fused_gate_cumsum.py

[KDA] Fuse gate+cumsum and reuse chunk index for KDA (#23038)

2026-04-21 17:54:20 +08:00

bench_gdn_decode.py

[GDN] Support GDN packed decode (#20627)

2026-03-18 13:20:07 +08:00

bench_gdn_prefill_cutedsl.py

[GDN] Support SM100 CuTeDSL GDN Prefill Kernel (#26200)

2026-05-26 15:38:29 +08:00

bench_gdn_prefill.py

[GDN] Add benchmark for sglang gdn prefill (#20428)

2026-03-12 22:25:02 +08:00

bench_gdn_qkv_split.py

[GDN] Optimize prefill QKV split dispatch (#26206)

2026-06-02 16:48:31 +08:00

bench_int8_checkpoint_reuse.py

[GDN][KDA][mem_cache] int8 checkpoint pool for the linear-attn prefix cache (#28185)

2026-06-17 20:41:46 -07:00

bench_kda_decode.py

[KDA] Support KDA packed decode (#26586)

2026-06-01 16:52:01 +08:00

bench_kda_prefill_cutedsl.py

[KDA] Add CuteDSL Prefill Kernel on SM100 (#27488)

2026-06-10 21:25:19 +08:00