Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
drbh
/
yamoe
like
2
kernel
License:
mit
Model card
Files
Files and versions
xet
Community
1
main
yamoe
126 kB
2 contributors
History:
11 commits
drbh
fix: improve layer for transformer integration
bd058af
5 months ago
build
feat: adjust reference impl
5 months ago
csrc
feat: impl backward experts
5 months ago
torch-ext
fix: improve layer for transformer integration
5 months ago
.clang-format
8.1 kB
feat: yet another moe
5 months ago
.gitattributes
82 Bytes
feat: yet another moe
5 months ago
.gitignore
215 Bytes
fix: improve example output and allow pushing build
5 months ago
.pre-commit-config.yaml
216 Bytes
feat: yet another moe
5 months ago
README.md
4.8 kB
fix: link to kernel hub
5 months ago
build.toml
578 Bytes
fix: improve layer for transformer integration
5 months ago
compare_example.py
10.9 kB
fix: prefer hub kernel build
5 months ago
flake.lock
4.45 kB
fix: improve layer for transformer integration
5 months ago
flake.nix
463 Bytes
feat: yet another moe
5 months ago
gpt_oss_backward.py
5.33 kB
fix: prefer hub kernel build
5 months ago
gpt_oss_match.py
3.87 kB
fix: prefer hub kernel build
5 months ago
perf_plot.py
18.7 kB
fix: bump to v0.2.0
5 months ago
readme_example.py
2.74 kB
fix: bump to v0.2.0
5 months ago