[Feature] support deepseek v3/r1/v3.2 (#78)

* [Feature] support deepseek v3/r1/v3.2

* fix gpt_oss

* update readme

* update readme

---------

Co-authored-by: hanhaowen <hanhaowen@baidu.com>
This commit is contained in:
baoqian426
2026-01-05 22:55:35 +08:00
committed by GitHub
parent 07bc24a555
commit ee0f50e68f
27 changed files with 5760 additions and 621 deletions

View File

@@ -417,7 +417,6 @@ class KunlunOps:
w1: torch.Tensor,
w2: torch.Tensor,
router_logits: torch.Tensor,
linear_weights: torch.Tensor,
ep_rank: int,
moe_top_k: int,
renormalize: bool,