Skip to content
image / Ubuntu / a3

[bugfix][torchair] fix wasted NPU memory buffer allocation for quantized deepseek with unquantized MTP layer #4029

Sign in to view logs

[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 #4029

Triggered via pull request September 20, 2025 14:38
@linfeng-yuanlinfeng-yuan
labeled #3068
linfeng-yuan:fix_torchair_redundant_process_group
Status Success
Total duration 31m 14s
Artifacts 1

image_a3_ubuntu.yml

on: pull_request
vllm-ascend image build
15m 41s
vllm-ascend image build
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size Digest
vllm-project~vllm-ascend~WVH2YI.dockerbuild
104 KB
sha256:55914fac11052e248e69bf069282a23c278a15c34bfd8c14978198d9a95e07cc