Skip to content
image / Ubuntu / a3

[bugfix][torchair] fix wasted NPU memory buffer allocation for quantized deepseek with unquantized MTP layer #4030

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 #4030

Triggered via pull request September 20, 2025 14:38
@linfeng-yuanlinfeng-yuan
labeled #3068
linfeng-yuan:fix_torchair_redundant_process_group
Status Cancelled
Total duration 15m 30s
Artifacts 1

image_a3_ubuntu.yml

on: pull_request
vllm-ascend image build
15m 28s
vllm-ascend image build
Fit to window
Zoom out
Zoom in

Annotations

1 error
image / Ubuntu / a3
Canceling since a higher priority waiting request for image / Ubuntu / a3-refs/pull/3068/merge exists

Artifacts

Produced during runtime
Name Size Digest
vllm-project~vllm-ascend~CYQXFM.dockerbuild
104 KB
sha256:7938b26d382592ba14b0a7c40e61a1d3536a30a1f0a82ef4a3a598c3432b8179