llama-cpp-log-decoder 0.7.0

Decoder for the llama.cpp / ggml log callback stream
Documentation
  • Coverage
  • 2.44%
    1 out of 41 items documented0 out of 9 items with examples
  • Size
  • Source code size: 16.38 kB This is the summed size of all the files inside the crates.io package for this release.
  • Documentation size: 714.97 kB This is the summed size of all files generated by rustdoc for all configured targets
  • Ø build duration
  • this release: 5s Average build duration of successful builds.
  • all releases: 4s Average build duration of successful builds in releases after 2024-10-23.
  • Links
  • intentee/llama-cpp-bindings
    2 0 0
  • crates.io
  • Dependencies
    • —
  • Versions
  • Owners
  • mcharytoniuk

Decoder for the llama.cpp / ggml log callback stream.

The C side delivers log lines in fragments: a missing trailing newline signals that more fragments will follow at GGML_LOG_LEVEL_CONT. This crate is a pure &mut self transducer — feed (level, text) pairs, get complete LogLines back when the trailing newline arrives. No globals, no atomics, no FFI, no logger.