dhruvhead/ao - Morph

SIGN IN SIGN UP

dhruvhead / ao UNCLAIMED

0 0 0 Python

50 branches 107 tags

brrr cuda dtypes float8 inference llama mx pytorch quantization sparsity training transformer

Vasiliy Kuznetsov Stop quantize_ from leaking global fp32 matmul precision (complete fix) (#4643)

22705bd · 1d ago · 2,713 Commits

	.github
	benchmarks
	docs
	examples
	packaging
	scripts
	test
	third_party
	torchao
	tutorials
	.gitignore		6.0 KB
	.gitmodules		103 B
	.pre-commit-config.yaml		1016 B
	CITATION.cff		335 B
	CLAUDE.md		2.0 KB
	CODE_OF_CONDUCT.md		3.5 KB
	CODEOWNERS		956 B
	CONTRIBUTING.md		1.4 KB
	dev-requirements.txt		600 B
	LICENSE		1.5 KB
	pyproject.toml		376 B
	README.md		18.9 KB
	ruff.toml		358 B
	setup.py		32.8 KB
	version.txt		7 B