Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

[Neural Speed] Support continuous batching + beam search inference in LLAMA #417

[Neural Speed] Support continuous batching + beam search inference in LLAMA

[Neural Speed] Support continuous batching + beam search inference in LLAMA #417

Triggered via pull request March 1, 2024 02:37
Status Success
Total duration 7m 30s
Artifacts 2

cpp-graph-test.yml

on: pull_request
Matrix: CPP-Graph-Workflow
Genreate-Report
8s
Genreate-Report
Fit to window
Zoom out
Zoom in

Annotations

3 warnings
CPP-Graph-Workflow (gptj-6b)
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/checkout@v3, actions/upload-artifact@v3. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.
CPP-Graph-Workflow (llama-2-7b-chat)
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/checkout@v3, actions/upload-artifact@v3. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.
Genreate-Report
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/checkout@v3, actions/download-artifact@v3, dawidd6/action-download-artifact@v2, actions/upload-artifact@v3. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.

Artifacts

Produced during runtime
Name Size
FinalReport Expired
28.2 KB
cpp_graph Expired
1.92 KB