FP-Quant support #38696
SunMarc
merged
36 commits into
huggingface:main
from
BlackSamorez:main
quartet
62ea54b2
quartet qat -> quartet
dce76dea
format
de7cdd8a
bf16 backward
b5e2cfba
interfaces
9632a75e
forward_method
7199b608
quartet -> fp_quant
c2b5b29a
style
55cbb2a5
Merge branch 'huggingface:main' into main
d3409042
List -> list
72a6e4a9
list typing
9d6c3d75
Merge branch 'main' of github.com:BlackSamorez/transformers
7c381394
fixed format and annotations
53f19858
test_fp_quant
b7d7d3f5
docstrings and default dtypes
c0b7bfc7
Merge branch 'main' into main
294a4655
better docstring and removed noop checks
4dbbf100
docs
f666a49f
pseudoquantization support to test on non-blackwell
4089500a
SunMarc
approved these changes
on 2025-07-18
pseudoquant
fc2d60d8
Pseudoquant docs
02c924b8
Update docs/source/en/quantization/fp_quant.md
f8632736
BlackSamorez
commented
on 2025-07-18
Update docs/source/en/quantization/fp_quant.md
c234f02d
BlackSamorez
commented
on 2025-07-18
Update docs/source/en/quantization/fp_quant.md
52c8bd1c
Update src/transformers/utils/quantization_config.py
709b2e61
Update tests/quantization/fp_quant_integration/test_fp_quant.py
f3df44b2
Update tests/quantization/fp_quant_integration/test_fp_quant.py
aa3d3c8c
small test fixes
76810b83
dockerfile update
e8f1192b
Merge branch 'main' of github.com:BlackSamorez/transformers
1d31865a
spec link
b92ab57b
removed `_process_model_after_weight_loading`
22ba0b4d
Merge branch 'main' into main
ff03597d
SunMarc
approved these changes
on 2025-07-22
toctree
235fc603
Merge branch 'main' of github.com:BlackSamorez/transformers
56402821
disabled auto-merge 250 days ago
Head branch was pushed to by a user without write access
Head branch was pushed to by a user without write access
Merge branch 'main' into main
5f87d900
Login to write a write a comment.
Login via GitHub