Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
optimum
/
llm-perf-leaderboard
like
396
Running
App
Files
Files
Community
34
main
llm-perf-leaderboard
/
src
6 contributors
History:
94 commits
baptistecolle
HF staff
Add torchao int4 weight only quantization as an option (
#34
)
8766911
verified
14 days ago
assets.py
Safe
1.05 kB
update
7 months ago
attention.py
Safe
4.24 kB
update
7 months ago
content.py
Safe
2.89 kB
add support for additional backends (#33)
about 2 months ago
dependency.py
Safe
65 Bytes
add support for additional backends (#33)
about 2 months ago
hardware.py
Safe
1 kB
add support for additional backends (#33)
about 2 months ago
kernels.py
Safe
5.3 kB
Add torchao int4 weight only quantization as an option (#34)
14 days ago
leaderboard.py
Safe
2.42 kB
update
7 months ago
llm_perf.py
Safe
5.32 kB
add support for additional backends (#33)
about 2 months ago
map.py
Safe
1.97 kB
update
7 months ago
panel.py
Safe
9.58 kB
Add torchao int4 weight only quantization as an option (#34)
14 days ago
utils.py
Safe
3.51 kB
Add torchao int4 weight only quantization as an option (#34)
14 days ago