Lihengwannafly

``` %%init_spark launcher.num_executors = 18 launcher.executor_cores = 6 launcher.driver_memory = '30g' launcher.master = "yarn" launcher.jars = ["file:///root/spark-tensorflow-connector_2.11-1.14.0.jar"] ``` You can try this.

> Thanks for reporting. You can pass the model path as the specified HDFS path. > > We may add more detailed document about this soon. simple_tensorflow_serving --model_base_path="hdfs://GZGD/171587/1/model/NeuralCF/base-model-output" --model_platform="tensorflow" I...

> Could you please post the files in this HDFS directory? Try with `hadoop dfs -ls hdfs://GZGD/171587/1/model/NeuralCF/base-model-output`. > > We have to make sure that the output path is the...

> So the `1551684206` is the model version, right? And are there `saved_model.pb` and `variables` in these directories of the versions? yes, of course. By the way, I used pip...

Do you fix it?

> Should work, did you get any issue with this mode? I use redis(a python lib) like `from redis.sentinel import Sentinel` to implement it. And now I switch to pyspark,...

`export PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:32` I use a single card A100 to quantify the bloom176B model, and after I add this environment variable, the OOM issue gets skipped occasionally.

> Oh thank thank you @Lihengwannafly !哦谢谢谢谢！ > > Can I ask, how long did it take to quantise and pack the model?请问，模型量化打包用了多长时间？ when in 256 samples, it takes about...