mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-25 05:02:59 +08:00
This PR moves MTPSampler and derivatives to use the universal seq_slot indexing for sampling.
This is the last piece of the puzzle: After this, all of the samplers will use this format.
See:
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| draft_target.py | ||
| drafter.py | ||
| eagle3.py | ||
| interface.py | ||
| mtp.py | ||
| ngram.py | ||
| utils.py | ||