mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
9 lines
256 B
ReStructuredText
9 lines
256 B
ReStructuredText
Generation with Quantization
|
|
============================
|
|
|
|
Source https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llm-api/llm_quantization.py.
|
|
|
|
.. literalinclude:: ../../../examples/llm-api/llm_quantization.py
|
|
:language: python
|
|
:linenos:
|