diff --git a/Cargo.lock b/Cargo.lock index 6c92634..d6886cb 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -24,7 +24,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75" dependencies = [ "cfg-if", + "getrandom 0.3.4", "once_cell", + "serde", "version_check", "zerocopy", ] @@ -349,6 +351,15 @@ version = "0.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5" +[[package]] +name = "castaway" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dec551ab6e7578819132c713a93c022a05d60159dc86e7a7050223577484c55a" +dependencies = [ + "rustversion", +] + [[package]] name = "cc" version = "1.4.2" @@ -426,6 +437,21 @@ dependencies = [ "thiserror 2.0.20", ] +[[package]] +name = "compact_str" +version = "0.9.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9dfdd1c2274d9aa354115b09dc9a901d6c5576818cdf70d14cae2bdb47df00ab" +dependencies = [ + "castaway", + "cfg-if", + "itoa", + "rustversion", + "ryu", + "serde", + "static_assertions", +] + [[package]] name = "core-foundation-sys" version = "0.8.7" @@ -663,6 +689,12 @@ version = "0.1.7" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ef8ae57c4978a2acd8b869ce6b9ca1dfe817bff704c220209fdef2c0b75a01b9" +[[package]] +name = "daachorse" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6f55d7153ba3b507595872a3874803f07a8a81d1e888abed8e5db7da0597d6e2" + [[package]] name = "darling" version = "0.20.11" @@ -698,6 +730,15 @@ dependencies = [ "syn 2.0.119", ] +[[package]] +name = "dary_heap" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8b1e3a325bc115f096c8b77bbf027a7c2592230e70be2d985be950d3d5e60ebe" +dependencies = [ + "serde", +] + [[package]] name = "dashmap" version = "6.2.1" @@ -1582,15 +1623,6 @@ dependencies = [ "either", ] -[[package]] -name = "itertools" -version = "0.11.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b1c173a5686ce8bfa551b3563d0c2170bf24ca44da99c7ca4bfdab5418c3fe57" -dependencies = [ - "either", -] - [[package]] name = "itertools" version = "0.12.1" @@ -2401,12 +2433,12 @@ dependencies = [ [[package]] name = "rayon-cond" -version = "0.3.0" +version = "0.4.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "059f538b55efd2309c9794130bc149c6a553db90e9d99c2030785c82f0bd7df9" +checksum = "2964d0cf57a3e7a06e8183d14a8b527195c706b7983549cd5462d5aa3747438f" dependencies = [ "either", - "itertools 0.11.0", + "itertools 0.14.0", "rayon", ] @@ -2753,6 +2785,12 @@ version = "1.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596" +[[package]] +name = "static_assertions" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f" + [[package]] name = "statrs" version = "0.18.0" @@ -3958,22 +3996,24 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" [[package]] name = "tokenizers" -version = "0.20.4" +version = "0.23.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3b08cc37428a476fc9e20ac850132a513a2e1ce32b6a31addf2b74fa7033b905" +checksum = "44e5bea67576e04b6ff8564c5d9e09c2ef0cf476502245f2f120e497769d3112" dependencies = [ - "aho-corasick", + "ahash", + "compact_str", + "daachorse", + "dary_heap", "derive_builder", "esaxx-rs", - "getrandom 0.2.17", - "itertools 0.12.1", - "lazy_static", + "getrandom 0.3.4", + "itertools 0.14.0", "log", "macro_rules_attribute", "monostate", "onig", "paste", - "rand 0.8.7", + "rand 0.9.5", "rayon", "rayon-cond", "regex", @@ -3981,7 +4021,7 @@ dependencies = [ "serde", "serde_json", "spm_precompiled", - "thiserror 1.0.69", + "thiserror 2.0.20", "unicode-normalization-alignments", "unicode-segmentation", "unicode_categories", diff --git a/crates/stringcheese-tokenizer-hf-native/Cargo.toml b/crates/stringcheese-tokenizer-hf-native/Cargo.toml index 53c4b42..b046b4e 100644 --- a/crates/stringcheese-tokenizer-hf-native/Cargo.toml +++ b/crates/stringcheese-tokenizer-hf-native/Cargo.toml @@ -73,7 +73,7 @@ stringcheese-tokenizer = { workspace = true, features = ["std"] } # subset of tokenizers-rs's features governs which pipeline shape. # --------------------------------------------------------------------- [target.'cfg(not(target_family = "wasm"))'.dependencies] -tokenizers = { version = "0.20", default-features = false, features = ["onig", "esaxx_fast"] } +tokenizers = { version = "0.23", default-features = false, features = ["onig", "esaxx_fast"] } [target.'cfg(not(target_family = "wasm"))'.dev-dependencies] # Property tests exercise the byte-identical delegation contract over