flashinfer-ai/flashinfer - Morph

SIGN IN SIGN UP

flashinfer-ai / flashinfer

FlashInfer: Kernel Library for LLM Serving

0 0 0

37 branches 231 tags

attention cuda distributed-inference gpu jit large-large-models llm-inference moe nvidia pytorch

Sam (Kesen Li) fix: snap weight_scale_vec_size to handle block_scale_interleave padding for SM120 (#2898)

c4cb6e0 · 11h ago · 2,135 Commits

	.claude
	.devcontainer
	.github
	3rdparty
	benchmarks
	ci
	csrc
	docker
	docs
	flashinfer
	flashinfer-cubin
	flashinfer-jit-cache
	include
	licenses
	profiler
	scripts
	tests
	.clang-format		130 B
	.gitignore		3.7 KB
	.gitmodules		199 B
	.pre-commit-config.yaml		1.6 KB
	build_backend.py		5.7 KB
	build_utils.py		1.3 KB
	CLAUDE.md		21.7 KB
	CONTRIBUTING.md		6.8 KB
	Jenkinsfile		13.2 KB
	LICENSE		12.0 KB
	NOTICE		435 B
	pyproject.toml		3.0 KB
	pytest.ini		72 B
	README.md		10.0 KB
	requirements.txt		198 B
	version.txt		6 B