mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
9 lines
308 B
ReStructuredText
9 lines
308 B
ReStructuredText
Speculative Decoding
|
|
====================
|
|
Source https://github.com/NVIDIA/TensorRT-LLM/blob/a761585d9c15b4c1249aaf65a8f90764efa83a3c/examples/llm-api/llm_speculative_decoding.py.
|
|
|
|
.. literalinclude:: ../../../examples/llm-api/llm_speculative_decoding.py
|
|
:lines: 4-95
|
|
:language: python
|
|
:linenos:
|