EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Migrate XTorch operations to Kunlun operations (accelerating iteration) (#177)

Browse Source 
Signed-off-by: dongxinyu03 <dongxinyu03@baidu.com>
This commit is contained in:
Xinyu Dong
2026-02-12 18:13:00 +08:00
committed by GitHub
parent 744719587e
commit bf9369f733
15 changed files with 125 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_kunlun/ops/fla/fused_recurrent.py
View File

@@ -11,7 +11,7 @@ from typing import Optional
import torch
import xtorch_ops
import kunlun_ops
class FusedRecurrentFunction(torch.autograd.Function):
@@ -31,7 +31,7 @@ class FusedRecurrentFunction(torch.autograd.Function):
num_accepted_tokens: Optional[torch.Tensor] = None,
use_qk_l2norm_in_kernel: bool = False):
o, final_state = xtorch_ops.fused_recurrent_gated_delta_rule_fwdv2(
o, final_state = kunlun_ops.fused_recurrent_gated_delta_rule_fwdv2(
q.contiguous(),
k.contiguous(),
v.contiguous(),