[package] name = "xet-core-structures" version.workspace = true edition.workspace = true license.workspace = true homepage.workspace = true repository.workspace = true description = "Core data structures including MerkleHash, metadata shards, and Xorb objects." readme = "README.md" keywords = ["huggingface"] categories = ["artificial-intelligence", "data-structures"] [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 } 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] bytemuck = { 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 } half = { workspace = true } rand = { workspace = true } serde_json = { 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 = [] simulation = ["xet-runtime/simulation"]