|
c939307e8a
|
[MiniMax-M3] Overlap shared and routed experts (#34542)
Co-authored-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-08-14 22:01:48 +08:00 |
|
|
Roger Young
|
486c7de39f
|
Optimizing all_reduce in RMSNormTP in minimax_m2 (#16483)
|
2026-01-31 23:39:37 -08:00 |
|
|
Roger Youngandxuebi
|
d17b9e6392
|
Fusing RMSNormTP in minimax_m2 (#14416)
Co-authored-by: xuebi <xuebi@minimaxi.com>
|
2025-12-30 10:22:07 -08:00 |
|
|
|
5c64a20da7
|
Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#15538)
Co-authored-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2025-12-23 15:11:52 -08:00 |
|
|
Roger Youngandxuebi
|
3dabd609fb
|
Optimize topk sigmoid in minimax_m2 (#14047)
Co-authored-by: xuebi <xuebi@minimaxi.com>
|
2025-12-02 14:07:12 +08:00 |
|
|
Roger Youngandxuebi
|
e72cf13693
|
Support moe topk sigmoid kernel (#13049)
Co-authored-by: xuebi <xuebi@minimaxi.com>
|
2025-11-20 00:24:37 +08:00 |
|
|
Roger Young
|
dbd9435dc1
|
Fix mamba radix cache eviction logic in alloc_req_slots (#11616)
Signed-off-by: rogeryoungh <rogeryoungh@foxmail.com>
|
2025-10-23 13:07:43 -07:00 |
|