GitLab

[gpt-oss-120b] MoE configs for BW1000 TP=8

实现了用于优化张量计算的 rms_mrope_fuse 和 rms_mrope_fuse_fake 方法
更新了 forward：在满足条件时走新的 M-RoPE 融合路径
增强了 Qwen3MoeModel 对动态参数维度的支持，以适配该功能

update weights_not_loaded and flash_mla_with_kvcache
update paged_mqa_logits

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 19c58339)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
(cherry picked from commit d2dc5dfc)

Signed-off-by: sarathc-cerebras <sarath.chandran@cerebras.net>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
(cherry picked from commit 28d15ab5)

Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
(cherry picked from commit 11a89cf9)