TensorRT-LLMs/tensorrt_llm/models/redrafter
Ivan Sorokin d40fce474a
fix: redrafter sampling (#3278)
* Fix redrafter sampling

Signed-off-by: Ivan Sorokin <isorokin@nvidia.com>

* Rename redrafter bream search var

Signed-off-by: Ivan Sorokin <isorokin@nvidia.com>

* Remove _beam_search_candidates_v0

Signed-off-by: Ivan Sorokin <isorokin@nvidia.com>

* Remove unused import

Signed-off-by: Ivan Sorokin <isorokin@nvidia.com>

---------

Signed-off-by: Ivan Sorokin <isorokin@nvidia.com>
2025-04-08 07:49:32 +08:00
..
__init__.py Update TensorRT-LLM (#1954) 2024-07-16 15:30:25 +08:00
drafter.py Update TensorRT-LLM (#1954) 2024-07-16 15:30:25 +08:00
model.py Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +08:00
redrafter_helper.py fix: redrafter sampling (#3278) 2025-04-08 07:49:32 +08:00