MCPcopy
hub / github.com/NVIDIA/TensorRT-LLM / supports_inflight_batching

Function supports_inflight_batching

tensorrt_llm/_utils.py:840–844  ·  view source on GitHub ↗
(engine_dir)

Source from the content-addressed store, hash-verified

838
839
840def supports_inflight_batching(engine_dir):
841 config_path = Path(engine_dir) / "config.json"
842 json_config = GptJsonConfig.parse_file(config_path)
843 model_config = json_config.model_config
844 return model_config.supports_inflight_batching
845
846
847class QuantModeWrapper:

Callers 3

mainFunction · 0.90
mainFunction · 0.90
__init__Method · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected