🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
COMMITS
/ docker/transformers-quantization-latest-gpu/Dockerfile March 16, 2026
M
Bump torchao >=0.15 and fix quantization CI (#44604)
Marc Sun committed
February 24, 2026
J
Add Four Over Six quantization integration (#43970)
Jack Cook committed
February 12, 2026
Y
Fix docker files (#43946)
Yih-Dar committed
December 10, 2025
Q
Fully deprecate AutoGPTQ and AutoAWQ for GPT-QModel (#41567)
Qubitium-ModelCloud committed
November 4, 2025
A
[FPQuant] MXFP8 and MXFP4 backwards support (#41897)
Andrei Panferov committed
November 3, 2025
Y
Fix `torchcodec` version in quantization docker file (#41988)
Yih-Dar committed
November 2, 2025
Y
Fix `autoawq[kernels]` installation in quantization docker file (#41978)
Yih-Dar committed
October 10, 2025
M
Remove DISABLE_KERNEL_MAPPING flag (#41475)
Mohamed Mekkouri committed
October 1, 2025
A
FP-Quant NVFP4 and Python 3.9 support (#39876)
Andrei Panferov committed
September 29, 2025
M
Fix docker quantization (#41201)
Marc Sun committed
September 22, 2025
M
Update quantization CI (#41068)
Marc Sun committed
August 4, 2025
M
Fix quant docker for fp-quant (#39641)
Marc Sun committed
July 23, 2025
A
FP-Quant support (#38696)
Andrei Panferov committed
July 8, 2025
Q
Add torchcodec in docstrings/tests for `datasets` 4.0 (#39156)
Quentin Lhoest committed
June 27, 2025
M
Uninstallling Flash attention from quantization docker (#39078)
Mohamed Mekkouri committed
May 12, 2025
Y
uninstall `kernels` from docker images (#38083)
Yih-Dar committed
April 22, 2025
W
Add AutoRound quantization support (#37393)
Wenhua Cheng committed
April 11, 2025
M
Disable kernels for quantization (#37446)
Mohamed Mekkouri committed
March 20, 2025
F
Support loading Quark quantized models in Transformers (#36372)
fxmarty-amd committed
March 13, 2025
M
Upgrading torch version and cuda version in quantization docker (#36264)
Mohamed Mekkouri committed
February 17, 2025
M
Add compressed tensor in quant dockerfile (#36239)
Marc Sun committed
February 13, 2025
E
Efficient Inference Kernel for SpQR (#34976)
Elvir Crnčević committed
December 23, 2024
A
HIGGS Quantization Support (#34997)
Andrei Panferov committed
December 20, 2024
W
FEAT : Adding VPTQ quantization method to HFQuantizer (#34770)
wejoncy committed
November 28, 2024
M
Fix docker CI : install autogptq from source (#35000)
Mohamed Mekkouri committed
November 27, 2024
M
Fix : Add PEFT from source to CI docker (#34969)
Mohamed Mekkouri committed
November 25, 2024
M
Upgrade torch version to 2.5 in dockerfile for quantization CI (#34924)
Mohamed Mekkouri committed
B
[AWQ, CI] Bump AWQ version used in docker image (#34922)
Benjamin Bossan committed
October 24, 2024
Y
Drop support for Python 3.8 (#34314)
Yih-Dar committed
October 2, 2024
M
[Quantization] Switch to optimum-quanto (#31732)
Marc Sun committed
May 24, 2024
Y
Quantization / TST: Fix remaining quantization tests (#31000)
Younes Belkada committed
May 20, 2024
Y
FIX / Quantization: Fix Dockerfile build (#30890)
Younes Belkada committed
May 16, 2024
Y
TST / Quantization: Reverting to torch==2.2.1 (#30866)
Younes Belkada committed
May 15, 2024
Y
Use `torch 2.3` for CI (#30837)
Yih-Dar committed
May 2, 2024
M
Add HQQ quantization support (#29637)
mobicham committed
April 22, 2024
Z
[FEAT]: EETQ quantizer support (#30262)
zhong zhuang committed
April 9, 2024
M
Fix quantization tests (#29914)
Marc Sun committed
March 15, 2024
M
[Quantization] Quanto quantizer (#29023)
Marc Sun committed
March 5, 2024
I
Exllama kernels support for AWQ models (#28634)
Ilyas Moutawwakil committed
February 28, 2024
M
[CI] Quantization workflow (#29046)
Marc Sun committed