REZA ROKNI
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Robert Crowe2×
- Ahmet Altayonce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Demo: Deploying Gemma at dataflow scale | Gemma Developer Day 2024 | 2024-03-07 |
Pipeline reads two Pub/Sub topics with Apache Beam Python, decodes messages, and calls Gemma via the turnkey Dataflow RunInference transform running on… | ||
| ML Inference at scale, with Apache Beam and the Flink runner: Easy as learning your 5 times tables. | Flink Forward Global 2021 | 2021-10-18 |
Builds beam pipelines that run TensorFlow models with the Flink runner using the RunInference transform from tfx bsl, loading SavedModel from GCS in local mode… | ||
| Distributed Processing for Machine Learning Production Pipelines | Flink Forward Virtual 2020 | 2020-04-22 |
Claims that a production ML pipeline is practical end-to-end: they implement TFX components (ExampleGen→StatisticsGen→Transform→Trainer→Evaluator→Pusher) on… | ||
| nothing matches | ||