walrus-model 0.0.1

Walrus LLM provider implementations

Coverage
85.04%
108 out of 127 items documented0 out of 51 items with examples
Size
Source code size: 260.82 kB This is the summed size of all the files inside the crates.io package for this release.
Documentation size: 4.07 MB This is the summed size of all files generated by rustdoc for all configured targets
Ø build duration
this release: 3m 21s Average build duration of successful builds.
all releases: 1m 21s Average build duration of successful builds in releases after 2024-10-23.
Links
openwalrus/walrus
93 14 1
crates.io
Dependencies
Versions
Owners

walrus-model

LLM provider implementations for Walrus.

Supports DeepSeek, OpenAI-compatible, Claude, and local inference (via mistral.rs). Includes ProviderManager for multi-provider routing and ProviderConfig for configuration.

Features

local (default) — Local model inference via mistral.rs
cuda — NVIDIA CUDA GPU acceleration
metal — Apple Metal GPU acceleration

License

GPL-3.0