transformers/docs/source/en/quantization
Mohamed Mekkouri efe72fe21f
Adding FP8 Quantization to transformers (#36026)
* first commit

* adding kernels

* fix create_quantized_param

* fix quantization logic

* end2end

* fix style

* fix imports

* fix consistency

* update

* fix style

* update

* udpate after review

* make style

* update

* update

* fix

* update

* fix docstring

* update

* update after review

* update

* fix scheme

* update

* update

* fix

* update

* fix docstring

* add source

* fix test

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
2025-02-13 13:01:19 +01:00
..
aqlm.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
awq.md [docs] update awq doc (#36079) 2025-02-11 10:35:28 -08:00
bitnet.md FEAT : Adding BitNet quantization method to HFQuantizer (#33410) 2024-10-09 17:51:41 +02:00
bitsandbytes.md [docs] fix bugs in the bitsandbytes documentation (#35868) 2025-02-05 08:21:20 -08:00
compressed_tensors.md [docs] fix typo (#36080) 2025-02-07 12:42:09 -08:00
contribute.md Docs / Quantization: refactor quantization documentation (#30942) 2024-05-23 14:31:52 +02:00
eetq.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
fbgemm_fp8.md [docs] Increase visibility of torch_dtype="auto" (#35067) 2024-12-04 09:18:44 -08:00
finegrained_fp8.md Adding FP8 Quantization to transformers (#36026) 2025-02-13 13:01:19 +01:00
gptq.md Enable gptqmodel (#35012) 2025-01-15 14:22:49 +01:00
higgs.md HIGGS Quantization Support (#34997) 2024-12-23 16:54:49 +01:00
hqq.md Hqq serialization (#33141) 2024-09-30 14:47:18 +02:00
optimum.md Docs / Quantization: refactor quantization documentation (#30942) 2024-05-23 14:31:52 +02:00
overview.md Adding FP8 Quantization to transformers (#36026) 2025-02-13 13:01:19 +01:00
quanto.md [docs] Increase visibility of torch_dtype="auto" (#35067) 2024-12-04 09:18:44 -08:00
torchao.md Update torchao.md: use auto-compilation (#35490) 2025-01-14 11:33:48 +01:00
vptq.md FEAT : Adding VPTQ quantization method to HFQuantizer (#34770) 2024-12-20 09:45:53 +01:00