Chengze Fan
|
40b2119b23
|
[AMD] Cache AITER expert mask across decode (#31889)
|
2026-07-22 07:50:23 -07:00 |
|
Chengze Fan
|
122b3266a2
|
Add opt-in SGLANG_ROPE_CACHE_FP32 to keep RoPE cache in fp32 on non-CUDA (#29729)
|
2026-07-09 02:10:39 -07:00 |
|
Chengze Fan
|
43435a2f8e
|
[mori] Add a combine-kwargs hook and use_external_inp_buf plumbing (#29097)
|
2026-06-26 22:34:27 -07:00 |
|
Chengze Fan
|
19abebcc6a
|
[server_args] Make MoRI per-rank dispatch-token requirement overridable (#29096)
|
2026-06-26 22:25:36 -07:00 |
|
Chengze Fan
|
66ac385f52
|
fix(moe): MoRI EP init_mori_op missing BF16 dispatch branch (#28469)
Signed-off-by: Chengze Fan <fancz2002@gmail.com>
|
2026-06-16 21:02:06 -07:00 |
|
 Chengze FanandHaiShaw
|
8e836e7dc9
|
Support optional kwargs in AITER fused_moe runner (#26746)
Co-authored-by: HaiShaw <hixiao@gmail.com>
|
2026-06-04 08:25:03 -07:00 |
|