mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
5fa6fbd989
Fix AutoTuner warmup request generating. * The current warmup phase creates one request, which is insufficient for the warmup to cover the max_num_tokens. Revise the warmup phase to a batch of requests to cover the max_num_tokens to eliminate potential fallback cases. Refactor AutoTuner API and reduce host overhead. Refine (min, opt, max) values of optimization profile setup for get_valid_tactics to achieve the correct canImplement definition. * Refine cache key assembly process to reduce host overhead and simplify API. * Fix lru_cache usage to reduce host overhead. * Move tuning config initialization as a one-time object in tunable runner to reduce host overhead. Improve tuning config readability. * Use dataclass to define tuning config. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| _util.py | ||
| config_utils.py | ||
| config.py | ||
| cuda_graph_runner.py | ||
| guided_decoder.py | ||
| handle_context_logits.py | ||
| kv_cache_transceiver.py | ||
| layerwise_nvtx_marker.py | ||
| llm_request.py | ||
| model_engine.py | ||
| py_executor_creator.py | ||
| py_executor.py | ||
| resource_manager.py | ||
| sampler.py | ||
| scheduler.py | ||
| seq_slot_manager.py | ||