AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[quant] allow components_to_quantize to be a non-list for single components (#12234)

Browse Source 
* allow non list components_to_quantize.

* up

* Apply suggestions from code review

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* [docs] components_to_quantize (#12287)

init

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
This commit is contained in:
Sayak Paul
2025-09-11 01:17:08 +05:30
committed by GitHub
parent e1b7f1f240
commit eb7ef26736
6 changed files with 29 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/using-diffusers/text-img2vid.md
View File

@@ -98,7 +98,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_compute_dtype": torch.bfloat16
},
components_to_quantize=["transformer"]
components_to_quantize="transformer"
)
pipeline = HunyuanVideoPipeline.from_pretrained(