katgpt-types 0.2.0

Shared configuration, RNG, math utilities, LoRA, domain embeddings, and inference types for katgpt-rs / riir-engine. Pure substrate leaf — no katgpt-* deps.
Documentation
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.

[package]
edition = "2024"
name = "katgpt-types"
version = "0.2.0"
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Shared configuration, RNG, math utilities, LoRA, domain embeddings, and inference types for katgpt-rs / riir-engine. Pure substrate leaf — no katgpt-* deps."
readme = "README.md"
keywords = [
    "inference",
    "config",
    "rng",
    "lora",
    "modelless",
]
categories = [
    "data-structures",
    "science",
    "algorithms",
]
license = "MIT"
repository = "https://github.com/katopz/katgpt-rs"

[features]
belief_drafter = []
binary_plasma = []
collapse_aware_thinking = []
data_gate = []
default = []
deltanet_inference = []
depth_invariance = []
domain_latent = []
gpart_adapter = []
gpart_pruning = []
hydra_budget = []
loop_stability_fix = []
maxsim = []
plasma_path = []
rim_slots = []
sia_feedback = []
sigmoid_margin = ["maxsim"]
sparse_mlp = []
spectral_threat = []
sr2am_configurator = []
wall_attention = []

[lib]
name = "katgpt_types"
path = "src/lib.rs"

[[example]]
name = "test_autovec"
path = "examples/test_autovec.rs"

[[test]]
name = "prof_f16_f16_kernel"
path = "tests/prof_f16_f16_kernel.rs"

[dependencies.blake3]
version = "1"

[dependencies.fastrand]
version = "2"

[dependencies.half]
version = "2"

[dependencies.rayon]
version = "1.10"

[dependencies.serde]
version = "1"
features = ["derive"]