Efficient Inference Kernel for SpQR #34976
MekkCyber
merged
44 commits into
huggingface:main
from
elvircrn:spqr-quantizer
MekkCyber
commented
on 2024-12-09
stevhliu
commented
on 2025-01-09
Resolve vptq conflict
7f4aa051
Rename spqr package to spqr_quant
ac4b1426
Get rid of aqlm mention
8c3f5f16
Start working on tests
ff61b8e9
Resolve ruff code checks
23c3a24a
Ruff format
0cb5ba7a
Isort
c980e667
Test updates
163983b9
Add gpu tag
f51d3d10
Rename to modules_to_not_convert
24ca92f4
Config update
913fbcb3
Docs and config update
d4331652
Docs and config update
5582beb1
Update to update_torch_dtype
3d64f881
spqr config parameter validation
81237de9
Ruff update
1dacd501
Apply ruff fixes
c1a4304f
Test fixes
53c53c06
Ruff update
c21c4129
Mark tests as @slow again; Ruff; Docstring update
dc89200e
Ruff
64929f7e
Remove absolute path
fada970a
Resolve typo
4694339a
Remove redundandt log
92ea4934
Check accelerate/spqr availability
14944538
Ruff fix
9e8f4707
Check if the config contains proper shapes
525dcdfe
Ruff test
1a54d862
Documentation update
68afc893
overview update
0eff9441
Ruff checks
82e7f4e7
Ruff code quality
274d3683
Make style
a630d6d2
Update docs/source/en/quantization/spqr.md
96b2613f
Update spqr.md
17d1c72a
Enable gptqmodel (#35012)
55b50c70
Fix : Nemotron Processor in GGUF conversion (#35708)
c4273e27
Merge branch 'main' into spqr-quantizer
5aac5e3e
Update docs/source/en/quantization/spqr.md
95d2e743
Add missing TOC to doc
3fdc0c38
Merge branch 'huggingface:main' into spqr-quantizer
14f21c1b
Merge branch 'main' into spqr-quantizer
cdefeafe
Merge branch 'main' into spqr-quantizer
8da4a66e
Merge branch 'main' into spqr-quantizer
afff70ea
SunMarc
approved these changes
on 2025-02-13
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub