3 Star 11 Fork 6

Gitee 极速下载/huggingface-transformers

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
此仓库是为了提升国内下载速度的镜像仓库,每日同步一次。 原始仓库: https://github.com/huggingface/transformers
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README

Benchmarks

You might want to add new benchmarks.

You will need to define a python function named run_benchmark in your python file and the file must be located in this benchmark/ directory.

The expected function signature is the following:

def run_benchmark(logger: Logger, branch: str, commit_id: str, commit_msg: str, num_tokens_to_generate=100):

Writing metrics to the database

MetricsRecorder is thread-safe, in the sense of the python Thread. This means you can start a background thread to do the readings on the device measurements while not blocking the main thread to execute the model measurements.

cf llama.py to see an example of this in practice.

from benchmarks_entrypoint import MetricsRecorder
import psycopg2

def run_benchmark(logger: Logger, branch: str, commit_id: str, commit_msg: str, num_tokens_to_generate=100):
  metrics_recorder = MetricsRecorder(psycopg2.connect("dbname=metrics"), logger, branch, commit_id, commit_msg)
  benchmark_id = metrics_recorder.initialise_benchmark({"gpu_name": gpu_name, "model_id": model_id})
    # To collect device measurements
    metrics_recorder.collect_device_measurements(
        benchmark_id, cpu_util, mem_megabytes, gpu_util, gpu_mem_megabytes
    )
    # To collect your model measurements
    metrics_recorder.collect_model_measurements(
        benchmark_id,
        {
            "model_load_time": model_load_time,
            "first_eager_forward_pass_time_secs": first_eager_fwd_pass_time,
            "second_eager_forward_pass_time_secs": second_eager_fwd_pass_time,
            "first_eager_generate_time_secs": first_eager_generate_time,
            "second_eager_generate_time_secs": second_eager_generate_time,
            "time_to_first_token_secs": time_to_first_token,
            "time_to_second_token_secs": time_to_second_token,
            "time_to_third_token_secs": time_to_third_token,
            "time_to_next_token_mean_secs": mean_time_to_next_token,
            "first_compile_generate_time_secs": first_compile_generate_time,
            "second_compile_generate_time_secs": second_compile_generate_time,
            "third_compile_generate_time_secs": third_compile_generate_time,
            "fourth_compile_generate_time_secs": fourth_compile_generate_time,
        },
    )
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Python
1
https://gitee.com/mirrors/huggingface-transformers.git
git@gitee.com:mirrors/huggingface-transformers.git
mirrors
huggingface-transformers
huggingface-transformers
main

搜索帮助