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This repository has been archived by the owner on Oct 11, 2024.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

Commit

Permalink
Update conftest.py
Browse files Browse the repository at this point in the history
  • Loading branch information
@robertgshaw2-neuralmagic
robertgshaw2-neuralmagic authored Jul 2, 2024
1 parent 484a2e3 commit 99f1474
Showing 1 changed file with 3 additions and 2 deletions.
5 changes: 3 additions & 2 deletions tests/conftest.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
from functools import cached_property
from pathlib import Path
from typing import (TYPE_CHECKING, Any, Dict, List, Literal, Optional, Tuple,
TypedDict, TypeVar)
TypedDict, TypeVar)

import pytest
import torch
Expand Down Expand Up @@ -87,7 +87,8 @@ class _ImageAssetPrompts(TypedDict):
cherry_blossom: str


class _ImageAssets(UserList[ImageAsset]):
# UPSTREAM SYNC: Error in Python3.8 without Any
class _ImageAssets(UserList[Any]):

def __init__(self) -> None:
super().__init__(
Expand Down

1 comment on commit 99f1474

@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: 99f1474 Previous: 569c905 Ratio
{"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"} 187.2315818866764 ms 183.7486813564707 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"} 85.92061304146813 ms 83.87263279896116 ms 1.02
{"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"} 25.74610043665416 ms 24.654848356343184 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"} 6.352810349622611 ms 6.001352674302764 ms 1.06

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

Please sign in to comment.