Merge branch 'main' into simple-githash-embed

neuralmagic · Jun 27, 2024 · 97b1890 · 97b1890 · github-actions · Jun 27, 2024
2 parents 0e7c4f6 + 80701e4
commit 97b1890
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 4 deletions.
diff --git a/.github/actions/nm-get-docker-tags/action.yml b/.github/actions/nm-get-docker-tags/action.yml
@@ -15,7 +15,7 @@ outputs:
     description: "extra tag for the docker image based on build type, either latest (for RELEASE) or nightly (for NIGHTLY)"
     value: ${{ steps.tags.outputs.extra_tag }}
   build_version:
-    "version of nm-vllm, e.g. 0.4.0, 0.4.0.20240531"
+    description: "version of nm-vllm, e.g. 0.4.0, 0.4.0.20240531"
     value: ${{ steps.tags.outputs.build_version }}
 runs:
   using: composite

diff --git a/.github/actions/nm-summary-build/action.yml b/.github/actions/nm-summary-build/action.yml
@@ -20,8 +20,6 @@ runs:
   using: composite
   steps:
   - run: |
-      BUILD_STATUS=${{ inputs.build_status }}
-      BUILD_EMOJI=$(./.github/scripts/step-status ${BUILD_STATUS})
       WHL_STATUS=${{ inputs.whl_status }}
       WHL_EMOJI=$(./.github/scripts/step-status ${WHL_STATUS})
       echo "testmo URL: ${{ inputs.testmo_run_url }}" >> $GITHUB_STEP_SUMMARY

diff --git a/.github/scripts/step-status b/.github/scripts/step-status
@@ -5,7 +5,7 @@
 
 STEP_STATUS=${1}
 
-if [ $STEP_STATUS -eq 0 ]; then
+if [ "$STEP_STATUS" -eq 0 ]; then
     # green check
     echo -e "\xE2\x9C\x85"
 else
Benchmark suite	Current: `97b1890`	Previous: `4ab3b8a`	Ratio
`{"name": "request_throughput", "description": "VLLM Engine throughput - synthetic\nmodel - NousResearch/Llama-2-7b-chat-hf\nmax_model_len - 4096\nbenchmark_throughput {\n \"use-all-available-gpus_\": \"\",\n \"input-len\": 256,\n \"output-len\": 128,\n \"num-prompts\": 1000\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"}`	`2.4621964989259952` prompts/s	`2.50032143674207` prompts/s	`1.02`
`{"name": "token_throughput", "description": "VLLM Engine throughput - synthetic\nmodel - NousResearch/Llama-2-7b-chat-hf\nmax_model_len - 4096\nbenchmark_throughput {\n \"use-all-available-gpus_\": \"\",\n \"input-len\": 256,\n \"output-len\": 128,\n \"num-prompts\": 1000\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"}`	`945.4834555875822` tokens/s	`960.1234317089549` tokens/s	`1.02`