mirror of
https://github.com/huggingface/xet-core.git
synced 2026-06-04 13:30:29 +08:00
602d7679f6
Currently, the full test validation is rather heavy, but running local
tests often fails to catch many issues due to the tests that probe the
full stack. This PR adds a smoke-test path that runs a meaningful subset
of the tests across the workspace that covers most errors. This runs in
about 1/8 of the time as cargo test, so it's useful to use in speeding
up AI model iteration.
In addition, a few intermittent failures were also fixed.
There should be no runtime functionality change.
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Low Risk**
> Low risk since changes are limited to Cargo configuration and test
gating; no production code paths are modified. Main risk is accidentally
skipping too much coverage or misconfiguring feature flags in CI/local
workflows.
>
> **Overview**
> Adds a new `cargo smoke-test` workflow by introducing a `smoke-test`
Cargo profile and a `cargo` alias that runs `test` with per-crate
`smoke-test` features enabled.
>
> Defines `smoke-test` features across multiple crates and uses
`#[cfg_attr(feature = "smoke-test", ignore)]` / `#[cfg(... not(feature =
"smoke-test"))]` to skip long-running, concurrency-heavy, or full-stack
integration tests during smoke runs.
>
> Tightens test robustness by making `SafeFileCreator` permission
assertions umask-tolerant (require owner read/write rather than an exact
`0o644`).
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
5d53009652. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Hoyt Koepke <hoytak@xethub.com>
89 lines
2.5 KiB
TOML
89 lines
2.5 KiB
TOML
[package]
|
|
name = "xet-core-structures"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
description = "Core data structures including MerkleHash, metadata shards, and xorb objects"
|
|
|
|
[lib]
|
|
name = "xet_core_structures"
|
|
path = "src/lib.rs"
|
|
|
|
[[bench]]
|
|
name = "compression_bench"
|
|
harness = false
|
|
bench = true
|
|
|
|
[[bench]]
|
|
name = "bg_split_regroup_bench"
|
|
harness = false
|
|
bench = true
|
|
|
|
[dependencies]
|
|
xet-runtime = { version = "1.4.0", path = "../xet_runtime" }
|
|
|
|
async-trait = { workspace = true }
|
|
base64 = { workspace = true }
|
|
blake3 = { workspace = true }
|
|
bytes = { workspace = true }
|
|
clap = { workspace = true }
|
|
countio = { workspace = true }
|
|
csv = { workspace = true }
|
|
futures = { workspace = true }
|
|
futures-util = { workspace = true }
|
|
half = { workspace = true }
|
|
heapify = { workspace = true }
|
|
itertools = { workspace = true }
|
|
lazy_static = { workspace = true }
|
|
lz4_flex = { workspace = true }
|
|
more-asserts = { workspace = true }
|
|
rand = { workspace = true, features = ["small_rng"] }
|
|
regex = { workspace = true }
|
|
safe-transmute = { workspace = true }
|
|
serde = { workspace = true }
|
|
static_assertions = { workspace = true }
|
|
tempfile = { workspace = true }
|
|
thiserror = { workspace = true }
|
|
tracing = { workspace = true }
|
|
|
|
[target.'cfg(not(target_family = "wasm"))'.dependencies]
|
|
bincode = { workspace = true }
|
|
bytemuck = { workspace = true }
|
|
heed = { workspace = true }
|
|
tokio = { workspace = true, features = ["time", "rt", "macros", "sync", "test-util", "io-util", "rt-multi-thread"] }
|
|
tokio-util = { workspace = true, features = ["io"] }
|
|
uuid = { workspace = true, features = ["v4"] }
|
|
|
|
[target.'cfg(target_family = "wasm")'.dependencies]
|
|
getrandom = { workspace = true, features = ["wasm_js"] }
|
|
tokio = { workspace = true, features = ["sync", "macros", "io-util", "rt", "time"] }
|
|
uuid = { workspace = true, features = ["v4", "js"] }
|
|
web-time = { workspace = true }
|
|
|
|
[dev-dependencies]
|
|
bincode = { workspace = true }
|
|
futures-util = { workspace = true }
|
|
rand = { workspace = true }
|
|
serial_test = { workspace = true }
|
|
tokio = { workspace = true, features = ["rt-multi-thread", "macros"] }
|
|
|
|
[target.'cfg(not(target_family = "wasm"))'.dev-dependencies]
|
|
tempfile = { workspace = true }
|
|
|
|
[[bin]]
|
|
name = "shard_benchmark"
|
|
path = "src/metadata_shard/shard_benchmark.rs"
|
|
|
|
[[bin]]
|
|
path = "src/xorb_object/byte_grouping/compression_stats/collect_compression_stats.rs"
|
|
name = "collect_compression_stats"
|
|
|
|
[[bin]]
|
|
path = "src/xorb_object/byte_grouping/bg4_prediction_benchmark.rs"
|
|
name = "bg4_prediction_benchmark"
|
|
|
|
[features]
|
|
strict = []
|
|
smoke-test = []
|