mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
e12e7a753d
* refactor: Expose DecoderState via bindings and integrate in TRTLLMDecoder - Introduced a new `DecoderState` class in the C++ bindings, encapsulating key functionalities for managing decoding state. - Adjusted the Python `TRTLLMDecoder` to access properties from `decoder_state`, ensuring consistency and clarity in the decoding process. These changes streamline the decoder's architecture and enhance maintainability. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove unused new_tokens from DecoderState bindings Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| attention_backend | ||
| auto_deploy | ||
| compilation | ||
| custom_ops | ||
| models | ||
| modules | ||
| pyexecutor | ||
| speculative | ||
| __init__.py | ||
| autotuner.py | ||
| distributed.py | ||
| llm.py | ||
| metadata.py | ||
| model_config.py | ||
| pipeline_interface.py | ||
| utils.py | ||