fix: vectorize 3-bit and 6-bit bitstream packing (~1900× speedup) #50

	name: CI

	on:
	push:
	branches: [main]
	pull_request:
	branches: [main]

	env:
	FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true

	jobs:
	lint:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: "3.12"
	- run: pip install ruff
	- run: ruff check .

	test-linux:
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix:
	python-version: ["3.10", "3.11", "3.12"]
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: ${{ matrix.python-version }}
	- name: Install dependencies
	run: pip install -e ".[dev]"
	- name: Run tests (torch only)
	run: \|
	pytest tests/ \
	--ignore=tests/test_e2e_models.py \
	--ignore=tests/test_e2e_large_models.py \
	--ignore=tests/test_cache_mlx.py \
	-v --tb=short

	test-macos:
	runs-on: macos-latest
	strategy:
	fail-fast: false
	matrix:
	python-version: ["3.11", "3.12"]
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: ${{ matrix.python-version }}
	- name: Install dependencies
	run: \|
	pip install -e ".[dev]"
	pip install mlx mlx-lm
	- name: Run tests (torch + MLX)
	run: \|
	pytest tests/ \
	--ignore=tests/test_e2e_models.py \
	--ignore=tests/test_e2e_large_models.py \
	-v --tb=short

Navigation Menu