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This repository has been archived by the owner on Oct 11, 2024.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

dbarbuzzi triggered nightly on refs/heads/main #137

dbarbuzzi triggered nightly on refs/heads/main

dbarbuzzi triggered nightly on refs/heads/main #137

Triggered via schedule May 22, 2024 01:25
Status Failure
Total duration 19h 31m 18s
Artifacts 6

nightly.yml

on: schedule
BUILD-TEST  /  ...  /  BENCHMARK
5h 28m
BUILD-TEST / BENCHMARK / BENCHMARK
BUILD-TEST  /  ...  /  TEST
4h 4m
BUILD-TEST / TEST-SOLO / TEST
BUILD-TEST  /  ...  /  TEST
6h 10m
BUILD-TEST / TEST-MULTI / TEST
BUILD-TEST  /  ...  /  TEST-ACCURACY-SMOKE
8m 23s
BUILD-TEST / TEST-ACCURACY-SMOKE / TEST-ACCURACY-SMOKE
BUILD-TEST  /  ...  /  TEST-ACCURACY-FULL
BUILD-TEST / TEST-ACCURACY-FULL / TEST-ACCURACY-FULL
BUILD-TEST  /  ...  /  BENCHMARK_REPORT
32s
BUILD-TEST / BENCHMARK / BENCHMARK_REPORT
BUILD-TEST  /  ...  /  PUBLISH
21s
BUILD-TEST / PUBLISH / PUBLISH
Fit to window
Zoom out
Zoom in

Annotations

1 error and 1 warning
BUILD-TEST / BENCHMARK / BENCHMARK_REPORT
# :warning: **Performance Alert** :warning: Possible performance regression was detected for benchmark **'smaller_is_better'**. Benchmark result of this commit is worse than the previous benchmark result exceeding threshold `1.10`. | Benchmark suite | Current: 93183d6b21fd1f42fc2a98b93e46fca0c5530b40 | Previous: d69a34a3194efb8dd34c1f293af91aac19b5b992 | Ratio | |-|-|-|-| | `{"name": "median_ttft_ms", "description": "VLLM Serving - Dense\nmodel - teknium/OpenHermes-2.5-Mistral-7B\nmax-model-len - 4096\nsparsity - None\nbenchmark_serving {\n \"nr-qps-pair_\": \"300,1\",\n \"dataset\": \"sharegpt\"\n}", "gpu_description": "NVIDIA A10G x 1", "vllm_version": "0.3.0", "python_version": "3.10.12 (main, May 10 2024, 13:42:25) [GCC 9.4.0]", "torch_version": "2.3.0+cu121"}` | `90.02754549999281` ms | `81.75302800009376` ms | `1.10` | This comment was automatically generated by [workflow](https://github.com/neuralmagic/nm-vllm/actions?query=workflow%3ANightly) using [github-action-benchmark](https://github.com/marketplace/actions/continuous-benchmark). Comment was generated at https://github.com/neuralmagic/nm-vllm/commit/93183d6b21fd1f42fc2a98b93e46fca0c5530b40#commitcomment-142267648
BUILD-TEST / BENCHMARK / BENCHMARK_REPORT
Performance alert! Previous value was 81.75302800009376 and current value is 90.02754549999281. It is 1.1012135905215592x worse than previous exceeding a ratio threshold 1.1

Artifacts

Produced during runtime
Name Size
3.10.12-nm-vllm-nightly-0.3.0.20240522.tar.gz Expired
535 KB
9183880937-aws-avx2-32G-a10g-24G Expired
124 KB
cc-vllm-html-aws-avx2-192G-4-a10g-96G Expired
2.23 MB
cc-vllm-html-aws-avx2-32G-a10g-24G Expired
2.23 MB
gh_action_benchmark_jsons-9183880937-aws-avx2-32G-a10g-24G Expired
28.5 KB
nm_vllm_nightly-0.3.0.20240522-cp310-cp310-manylinux_2_17_x86_64.whl Expired
103 MB