TensorRT-LLMs/tensorrt_llm/tools/layer_wise_benchmarks
Tailing Yuan a7fe043b13
[None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts (#10237)
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
2026-01-05 11:23:04 +08:00
..
__init__.py [None][feat] Add a parser to layer-wise benchmarks (#9440) 2025-11-25 05:45:16 -08:00
deepseekv3_runner.py [None][feat] Add weights initialization and context phase parser to layer-wise benchmarks (#9667) 2025-12-04 13:41:15 +08:00
mark_utils.py [None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts (#10237) 2026-01-05 11:23:04 +08:00
qwen3_next_runner.py [None][feat] Add weights initialization and context phase parser to layer-wise benchmarks (#9667) 2025-12-04 13:41:15 +08:00
runner_factory.py [None][feat] Add Qwen3-Next to layer-wise benchmarks (#9065) 2025-11-14 10:03:00 +08:00
runner_interface.py [None][feat] Add a parser to layer-wise benchmarks (#9440) 2025-11-25 05:45:16 -08:00
runner_utils.py [None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts (#10237) 2026-01-05 11:23:04 +08:00