mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-29 23:23:48 +08:00
9 lines
272 B
ReStructuredText
9 lines
272 B
ReStructuredText
Speculative Decoding
|
|
====================
|
|
Source https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llm-api/llm_speculative_decoding.py.
|
|
|
|
.. literalinclude:: ../../../examples/llm-api/llm_speculative_decoding.py
|
|
:lines: 4-92
|
|
:language: python
|
|
:linenos:
|