Skip to content

[bugfix][torchair] fix wasted NPU memory buffer allocation for quantized deepseek with unquantized MTP layer #9632

[bugfix][torchair] fix wasted NPU memory buffer allocation for quantized deepseek with unquantized MTP layer

[bugfix][torchair] fix wasted NPU memory buffer allocation for quantized deepseek with unquantized MTP layer #9632

Triggered via pull request September 20, 2025 14:12
@linfeng-yuanlinfeng-yuan
synchronize #3068
Status Success
Total duration 8s
Artifacts

label_merge_conflict.yml

on: pull_request_target
Fit to window
Zoom out
Zoom in