Adding todo comment about client batch size support

triton-inference-server · May 21, 2024 · 90e06e2 · 90e06e2
1 parent 03d0097
commit 90e06e2
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/model_analyzer/config/generate/optuna_run_config_generator.py b/model_analyzer/config/generate/optuna_run_config_generator.py
@@ -281,6 +281,7 @@ def _create_perf_analyzer_config(
 
         perf_analyzer_config.update_config_from_profile_config(model_name, self._config)
 
+        # TODO: TMA-1934 add support for user specifying a range of client batch sizes
         perf_config_params = {
             "batch-size": DEFAULT_BATCH_SIZES,
             "concurrency-range": concurrency,