mirror of
https://github.com/huggingface/xet-core.git
synced 2026-06-04 13:30:29 +08:00
45d38a13a9
This PR is a massive rearrangement of the code base into 5 packages intended for release on cargo. The directories and corresponding packages are: 1. xet_runtime/ — compiles into the xet-runtime package. Contains the runtime, config, and logging management. 2. xet_core_structures/ — compiles into the xet-core-structures package. Contains core data structures for hashing, shards, and xorbs as well as internal data structures that depend on these. 3. xet_client/ — compiles into the xet-client package, contains client code for remotely connecting to the Hugging Face servers. 4. xet_data/ — compiles into the xet-data package, contains the data processing pipeline: chunking/deduplication, file reconstruction, clean/smudge operations, and progress tracking. 5. xet_pkg/ — compiles into the hf-xet package, provides the top-level session-based API for file upload and download with user-facing error categorization. This is the primary package downstream dependencies would use. This also contains a single summary error type, XetError, that translates cleanly into python error types. In addition, the other tools are: - git_xet/ — the git_xet CLI binary crate (location preserved). - hf_xet/ -- the hf_xet python package (location preserved). - simulation/ — the simulation crate for upload scenario benchmarking. - wasm/ -- the wasm objects. The full description — and information for an AI agent to use to update downstream dependencies — is at api_changes/update_260309_package_restructure.md. Summary of moves: - xet_runtime: became xet_runtime::core inside xet_runtime/. - utils: became xet_runtime::utils inside xet_runtime/. - xet_config: became xet_runtime::config inside xet_runtime/. - xet_logging: became xet_runtime::logging inside xet_runtime/. - error_printer: became xet_runtime::error_printer inside xet_runtime/. - file_utils: became xet_runtime::file_utils inside xet_runtime/. - merklehash: became xet_core_structures::merklehash inside xet_core_structures/. - mdb_shard: became xet_core_structures::metadata_shard inside xet_core_structures/. - xorb_object: became xet_core_structures::xorb_object inside xet_core_structures/. - cas_client: became xet_client::cas_client inside xet_client/. - hub_client: became xet_client::hub_client inside xet_client/. - cas_types: became xet_client::cas_types inside xet_client/. - chunk_cache: became xet_client::chunk_cache inside xet_client/. - data: became xet_data::processing inside xet_data/. - deduplication: became xet_data::deduplication inside xet_data/. - file_reconstruction: became xet_data::file_reconstruction inside xet_data/. - progress_tracking: became xet_data::progress_tracking inside xet_data/. - xet_session: became xet::xet_session inside xet_pkg/. - Wasm packages (hf_xet_wasm, hf_xet_thin_wasm): moved from top-level into wasm/; internal imports updated, public APIs unchanged.
121 lines
3.9 KiB
YAML
121 lines
3.9 KiB
YAML
name: xet-core CI
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- main
|
|
pull_request:
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
fmt:
|
|
name: Rustfmt
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
- uses: dtolnay/rust-toolchain@stable
|
|
with:
|
|
toolchain: nightly
|
|
components: rustfmt
|
|
- name: Format
|
|
run: |
|
|
cargo fmt --manifest-path ./Cargo.toml --all -- --check
|
|
cargo fmt --manifest-path ./hf_xet/Cargo.toml --all -- --check
|
|
detect-unused-dependencies:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
- name: Machete
|
|
uses: bnjbvr/cargo-machete@main
|
|
build_and_test-linux:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v6
|
|
- name: Install Rust 1.89
|
|
uses: dtolnay/rust-toolchain@1.89.0
|
|
with:
|
|
components: clippy
|
|
- uses: ./.github/actions/cache-rust-build
|
|
- name: Lint
|
|
run: |
|
|
cargo clippy -r --verbose -- -D warnings # elevates warnings to errors
|
|
cargo clippy -r --verbose --manifest-path hf_xet/Cargo.toml -- -D warnings # elevates warnings to errors
|
|
- name: Set up Git LFS
|
|
run: |
|
|
curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
|
|
sudo apt-get install git-lfs
|
|
git lfs install
|
|
- name: Build and Test
|
|
run: |
|
|
cargo test --verbose --no-fail-fast --features "strict git-xet-for-integration-test"
|
|
- name: Build and Test hf_xet
|
|
run: |
|
|
cd hf_xet && cargo test --verbose --no-fail-fast
|
|
- name: Check Cargo.lock has no uncommitted changes
|
|
run: |
|
|
# the build and test steps would update Cargo.lock if it is out of date
|
|
test -z "$(git status --porcelain Cargo.lock)" || (echo "Cargo.lock has uncommitted changes!" && exit 1)
|
|
build_and_test-win:
|
|
runs-on: windows-latest
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v6
|
|
- name: Install Rust 1.89
|
|
uses: dtolnay/rust-toolchain@1.89.0
|
|
with:
|
|
components: clippy
|
|
- uses: ./.github/actions/cache-rust-build
|
|
- name: Build and Test
|
|
run: |
|
|
cargo test --verbose --no-fail-fast --features "strict git-xet-for-integration-test"
|
|
- name: Build and Test hf_xet
|
|
run: |
|
|
cd hf_xet && cargo test --verbose --no-fail-fast
|
|
build_and_test-macos:
|
|
runs-on: macos-latest
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v6
|
|
- name: Install Rust 1.89
|
|
uses: dtolnay/rust-toolchain@1.89.0
|
|
with:
|
|
components: clippy
|
|
- name: Set up Git LFS
|
|
run: |
|
|
brew install git-lfs
|
|
git lfs install
|
|
- uses: ./.github/actions/cache-rust-build
|
|
- name: Build and Test
|
|
run: |
|
|
cargo test --verbose --no-fail-fast --features "strict git-xet-for-integration-test"
|
|
- name: Build and Test hf_xet
|
|
run: |
|
|
cd hf_xet && cargo test --verbose --no-fail-fast
|
|
build_and_test-wasm:
|
|
name: Build WASM
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v6
|
|
- name: Install Rust nightly
|
|
uses: dtolnay/rust-toolchain@nightly
|
|
with:
|
|
targets: wasm32-unknown-unknown
|
|
components: rust-src
|
|
- uses: ./.github/actions/cache-rust-build
|
|
- name: Install wasm-bindgen-cli and wasm-pack
|
|
run: |
|
|
cargo install --version 0.2.100 wasm-bindgen-cli
|
|
cargo install --version 0.13.1 wasm-pack
|
|
- name: Build hf_xet_thin_wasm
|
|
working-directory: wasm/hf_xet_thin_wasm
|
|
run: |
|
|
./build_wasm.sh
|
|
- name: Build hf_xet_wasm
|
|
working-directory: wasm/hf_xet_wasm
|
|
run: |
|
|
./build_wasm.sh |