Skip to content

[Attention][Kernel]moe support for llama4 and mllama4 #2136

[Attention][Kernel]moe support for llama4 and mllama4

[Attention][Kernel]moe support for llama4 and mllama4 #2136

Triggered via pull request May 12, 2025 13:04
Status Cancelled
Total duration 31m 3s
Artifacts

vllm_ascend_test.yaml

on: pull_request
Matrix: vLLM Ascend test
Fit to window
Zoom out
Zoom in

Annotations

5 errors
vLLM Ascend test (linux-arm64-npu-1, main)
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
vLLM Ascend test (linux-arm64-npu-1, main)
Canceling since a higher priority waiting request for pr-740 exists
vLLM Ascend test (linux-arm64-npu-1, v0.8.5.post1)
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
vLLM Ascend test (linux-arm64-npu-1, v0.8.5.post1)
Canceling since a higher priority waiting request for pr-740 exists
e2e test
Canceling since a higher priority waiting request for pr-740 exists