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This repository has been archived by the owner on Oct 11, 2024.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

Commit

Permalink
use v1.0.0 tag for nm-actions
Browse files Browse the repository at this point in the history
  • Loading branch information
dhuangnm authored and dhuangnm committed Jul 8, 2024
1 parent 537957c commit 87d5b1c
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 6 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/nm-build.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ jobs:

- name: set python
id: set_python
uses: neuralmagic/nm-actions/actions/set-python@main
uses: neuralmagic/nm-actions/actions/set-python@v1.0.0
with:
python: ${{ inputs.python }}
venv: ${{ env.VENV_BASE }}
Expand Down
7 changes: 2 additions & 5 deletions .github/workflows/nm-test.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -72,10 +72,7 @@ jobs:
python-version: ${{ inputs.python }}

- name: install automation components
run: |
sudo apt-get update --fix-missing
sudo apt-get install -y git-all
sudo apt-get install -y curl
uses: neuralmagic/nm-actions/actions/[email protected]

- name: checkout
id: checkout
Expand All @@ -94,7 +91,7 @@ jobs:
nvcc_threads: 0

- name: install testmo
uses: neuralmagic/nm-actions/actions/install-testmo@main
uses: neuralmagic/nm-actions/actions/install-testmo@v1.0.0

- name: create testmo run
id: create_testmo_run
Expand Down

1 comment on commit 87d5b1c

@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: 87d5b1c Previous: f6f2554 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"} 24.499484919998622 ms 24.363126653334653 ms 1.01
{"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"} 6.062676599480929 ms 6.047910136160147 ms 1.00
{"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"} 188.70118089333272 ms 184.3794278033306 ms 1.02
{"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"} 84.71225885242751 ms 85.039470859161 ms 1.00

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

Please sign in to comment.