diff --git a/Cargo.lock b/Cargo.lock index fe0ddb991..c3bbaba14 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -1256,6 +1256,12 @@ dependencies = [ "cmov", ] +[[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" @@ -1562,7 +1568,7 @@ dependencies = [ "safetensors", "serde", "serde_json", - "tokenizers", + "tokenizers 0.22.2", ] [[package]] @@ -1900,7 +1906,7 @@ dependencies = [ "tempfile", "thiserror 2.0.20", "tiktoken-rs", - "tokenizers", + "tokenizers 0.23.1", "toml", "tracing", "tree-sitter", @@ -4318,6 +4324,39 @@ dependencies = [ "derive_builder", "esaxx-rs", "getrandom 0.3.4", + "itertools 0.14.0", + "log", + "macro_rules_attribute", + "monostate", + "onig", + "paste", + "rand 0.9.4", + "rayon", + "rayon-cond", + "regex", + "regex-syntax", + "serde", + "serde_json", + "spm_precompiled", + "thiserror 2.0.20", + "unicode-normalization-alignments", + "unicode-segmentation", + "unicode_categories", +] + +[[package]] +name = "tokenizers" +version = "0.23.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "44e5bea67576e04b6ff8564c5d9e09c2ef0cf476502245f2f120e497769d3112" +dependencies = [ + "ahash", + "compact_str", + "daachorse", + "dary_heap", + "derive_builder", + "esaxx-rs", + "getrandom 0.3.4", "indicatif", "itertools 0.14.0", "log", diff --git a/crates/headroom-core/Cargo.toml b/crates/headroom-core/Cargo.toml index 903f4511f..d1488ef49 100644 --- a/crates/headroom-core/Cargo.toml +++ b/crates/headroom-core/Cargo.toml @@ -17,7 +17,7 @@ tiktoken-rs = "0.11" # `tokenizers` is the HuggingFace pure-Rust tokenizer crate. Default features # pull in `onig` for the BPE pre-tokenizer regex; that vendors oniguruma so it # builds without a system dep on macOS/Linux. -tokenizers = "0.22" +tokenizers = "0.23" # `hf-hub` is the HuggingFace Hub client. We use the blocking `ureq` transport # with `rustls` (no system OpenSSL dep — keeps the binary static-linkable for # AWS deploys). `from_pretrained` is called once at startup, so blocking is