 Yueming Yuan
|
cd075d1f64
|
[RL] convert DeepSeek V4 APE layout through weight loader (#27307)
|
2026-06-11 15:05:27 -07:00 |
|
|
Yueming Yuan
|
53a4b51f8c
|
Fix GLM NextN draft value head dim (#26049)
|
2026-06-09 16:13:37 -07:00 |
|
|
Yueming Yuan
|
4c8a022f38
|
Fix DeepSeek V4 DP reduce scatter when use attention DP + MoE TP (#27191)
|
2026-06-06 18:24:33 -07:00 |
|
|
Yueming Yuan
|
208397affc
|
[RL] [Spec v2] Use stop-aware seqlen for returned topk metadata (#26126)
|
2026-05-22 18:13:16 -07:00 |
|
|
Yueming Yuan
|
bd6c7e713c
|
[fix] Fallback DeepGEMM activation for unsupported shapes (#26025)
|
2026-05-22 09:01:40 +00:00 |
|