Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

Commit

Permalink
upload RELEASE wheel to pypi.org
Browse files Browse the repository at this point in the history
passing the workflow category and wheel file name to nm-upload-assets-to-gcp.yml workflow so that they can be used by the publish_whl action.
  • Loading branch information
derekk-nm committed Jul 3, 2024
1 parent 53347d5 commit 6218ac3
Show file tree
Hide file tree
Showing 2 changed files with 21 additions and 1 deletion.
2 changes: 2 additions & 0 deletions .github/workflows/nm-build-test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -169,6 +169,8 @@ jobs:
label: gcp-k8s-util
timeout: ${{ inputs.build_timeout }}
gitref: ${{ github.ref }}
wf_category: ${{ inputs.wf_category }}
whl: ${{ needs.BUILD.outputs.whl }}
secrets: inherit

# update docker
Expand Down
20 changes: 19 additions & 1 deletion .github/workflows/nm-upload-assets-to-gcp.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,14 @@ on:
description: 'git commit hash or branch name'
type: string
required: true

wf_category:
description: "workflow category: REMOTE, NIGHTLY, RELEASE"
type: string
default: "REMOTE"
whl:
description: "wheel file path"
type: string
required: true
jobs:

PUBLISH:
Expand Down Expand Up @@ -53,6 +60,16 @@ jobs:
with:
path: assets

- name: push wheel to pypi.org
# this workflow is only run if push-to-pypi is True, and we only
# want to push RELEASE wheels to the external pypi.org
if: ${{ inputs.wf_category }} == "RELEASE"
uses: neuralmagic/nm-actions/actions/publish_whl/action.yml@main
with:
username: ${{ secrets.PYPI_PUBLIC_USER }}
password: ${{ secrets.PYPI_PUBLIC_AUTH }}
whl: ${{ inputs.whl }}

# GCP
- name: 'Authenticate to Google Cloud'
id: auth
Expand All @@ -70,3 +87,4 @@ jobs:
- name: cp assets
id: cp-assets
uses: ./.github/actions/nm-cp-assets/

1 comment on commit 6218ac3

@github-actions
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

smaller_is_better

Benchmark suite Current: 6218ac3 Previous: 53347d5 Ratio
{"name": "mean_ttft_ms", "description": "VLLM Serving - Dense\nmodel - facebook/opt-350m\nmax-model-len - 2048\nsparsity - None\nbenchmark_serving {\n \"nr-qps-pair_\": \"300,1\",\n \"dataset\": \"sharegpt\"\n}", "gpu_description": "NVIDIA L4 x 1", "vllm_version": "0.5.1", "python_version": "3.10.12 (main, Jun 7 2023, 13:43:11) [GCC 11.3.0]", "torch_version": "2.3.0+cu121"} 24.74136927666071 ms 23.707702909998716 ms 1.04
{"name": "mean_tpot_ms", "description": "VLLM Serving - Dense\nmodel - facebook/opt-350m\nmax-model-len - 2048\nsparsity - None\nbenchmark_serving {\n \"nr-qps-pair_\": \"300,1\",\n \"dataset\": \"sharegpt\"\n}", "gpu_description": "NVIDIA L4 x 1", "vllm_version": "0.5.1", "python_version": "3.10.12 (main, Jun 7 2023, 13:43:11) [GCC 11.3.0]", "torch_version": "2.3.0+cu121"} 6.183022304156892 ms 5.927541407824298 ms 1.04
{"name": "mean_ttft_ms", "description": "VLLM Serving - Dense\nmodel - meta-llama/Meta-Llama-3-8B-Instruct\nmax-model-len - 4096\nsparsity - None\nbenchmark_serving {\n \"nr-qps-pair_\": \"300,1\",\n \"dataset\": \"sharegpt\"\n}", "gpu_description": "NVIDIA L4 x 1", "vllm_version": "0.5.1", "python_version": "3.10.12 (main, Jun 7 2023, 13:43:11) [GCC 11.3.0]", "torch_version": "2.3.0+cu121"} 187.70898154333813 ms 189.56996849333186 ms 0.99
{"name": "mean_tpot_ms", "description": "VLLM Serving - Dense\nmodel - meta-llama/Meta-Llama-3-8B-Instruct\nmax-model-len - 4096\nsparsity - None\nbenchmark_serving {\n \"nr-qps-pair_\": \"300,1\",\n \"dataset\": \"sharegpt\"\n}", "gpu_description": "NVIDIA L4 x 1", "vllm_version": "0.5.1", "python_version": "3.10.12 (main, Jun 7 2023, 13:43:11) [GCC 11.3.0]", "torch_version": "2.3.0+cu121"} 85.07850605865046 ms 84.82286798803653 ms 1.00

This comment was automatically generated by workflow using github-action-benchmark.

Please sign in to comment.