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

[310P]: add torch chunk gated delta rule and 910b parity ut (#7594)

Browse Source 
### What this PR does / why we need it?
RFC https://github.com/vllm-project/vllm-ascend/issues/7394
Add a PyTorch implementation of the  chunk gated delta rule on 310P.
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
UT

---------

Signed-off-by: Tflowers-0129 <2906339855@qq.com>
This commit is contained in:
Shaoxu Cheng
2026-03-25 16:46:43 +08:00
committed by GitHub
parent 17da96658f
commit e0e585a109
3 changed files with 388 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/_310p/ops/fla/__init__.py
View File

@@ -1,7 +1,9 @@
from .chunk_gated_delta_rule import chunk_gated_delta_rule_pytorch
from .fused_gdn_gating import fused_gdn_gating_pytorch
from .fused_recurrent_gated_delta_rule import fused_recurrent_gated_delta_rule_pytorch
__all__ = [
"fused_gdn_gating_pytorch",
"fused_recurrent_gated_delta_rule_pytorch",
"chunk_gated_delta_rule_pytorch",
]