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_integration

Skipping aqlm non working inference tests till fix merged (#34865)

2024-11-26 11:09:30 +01:00

autoawq

Enables CPU AWQ model with IPEX version. (#33460)

2024-10-04 16:25:10 +02:00

bitnet_integration

Fix : BitNet tests (#34895)

2024-11-25 16:47:14 +01:00

bnb

use torch.testing.assertclose instead to get more details about error in cis (#35659)

2025-01-24 16:55:28 +01:00

compressed_tensor

Run model as compressed/uncompressed mode (#34719)

2024-12-13 08:23:31 +01:00

eetq_integration

Fix typo in EETQ Tests (#35160)

2024-12-09 14:13:36 +01:00

fbgemm_fp8

Fix FbgemmFp8Linear not preserving tensor shape (#33239)

2024-09-11 13:26:44 +02:00

finegrained_fp8

Adding FP8 Quantization to transformers (#36026)

2025-02-13 13:01:19 +01:00

ggml

Fix words typos in ggml test. (#36060)

2025-02-06 15:32:40 +00:00

gptq

Enable gptqmodel (#35012)

2025-01-15 14:22:49 +01:00

higgs

HIGGS Quantization Support (#34997)

2024-12-23 16:54:49 +01:00

hqq

Fix : HQQ config when hqq not available (#35655)

2025-01-14 11:37:37 +01:00

quanto_integration

[tests] make cuda-only tests device-agnostic (#35607)

2025-01-13 14:48:39 +01:00

torchao_integration

Fix CI by tweaking torchao tests (#34832)

2024-11-20 20:28:51 +01:00

vptq_integration

Fix : VPTQ test (#35394)

2024-12-23 16:27:46 +01:00