Crate rlx_gpt_oss 

gpt-oss-20b runner.

gpt-oss ships as general.architecture = gpt-oss (or gpt_oss) in its GGUF converters. The 20B variant is an attention-only Llama-shaped decoder; this crate is a thin wrapper over rlx_llama32::Llama32Runner with arch validation.

Structs

GptOssRunner

GptOssRunnerBuilder

Llama32Runner

Llama32RunnerBuilder

Constants

FAMILY

PLAN_MILESTONE

Functions

cli_run

Type Aliases

Llama32ConfigSource

Where to load the Llama 3.2 config from.