infosave2007
243d8f4c7d
Docker / publish (push) Canceled after 0s
Release / crates-io (push) Canceled after 0s
Release / release (macos-14, aarch64-apple-darwin) (push) Canceled after 0s
Release / release (ubuntu-latest, x86_64-unknown-linux-gnu) (push) Canceled after 0s
Release / release (windows-latest, x86_64-pc-windows-msvc) (push) Canceled after 0s
- New Advanced controls on the import page: O(1) attention spec (off / all / deep N / explicit layer list) plus the --o1-m / --o1-window / --o1-sink knobs with validated defaults (32 / 128 / 4) and explanatory hints. - Backend passes --o1* to the native `cortiq convert`; fails fast with clear messages when combined with Python-only options, used on GGUF imports, or when the installed cortiq predates 0.2.0 (the hint needs the new runtime). - The hint is recorded in the .cmf header (weights byte-identical); the runtime applies it at load. Verified end-to-end: converted a model with --o1 all and the runtime logged "o1 nystrom attention: 2/2 layer(s)".
67 lines
1.8 KiB
TOML
67 lines
1.8 KiB
TOML
[package]
|
|
name = "cortiq-gateway"
|
|
version = "0.2.15"
|
|
edition = "2021"
|
|
rust-version = "1.75"
|
|
license = "Apache-2.0"
|
|
description = "Universal LLM gateway with intelligent routing and an embedded multilingual admin console"
|
|
repository = "https://github.com/infosave2007/cortiq-gateway"
|
|
homepage = "https://api.allaigate.com"
|
|
readme = "README.md"
|
|
keywords = ["llm", "gateway", "proxy", "openai", "routing"]
|
|
categories = ["web-programming::http-server", "command-line-utilities"]
|
|
# Files shipped in the published crate. The embedded admin SPA (web/) MUST be
|
|
# included because rust-embed compiles it in; docs/screenshots are excluded to
|
|
# keep the crate lean.
|
|
include = [
|
|
"src/**/*",
|
|
"web/**/*",
|
|
"config/gateway.example.toml",
|
|
"README.md",
|
|
"CHANGELOG.md",
|
|
"LICENSE",
|
|
]
|
|
|
|
[dependencies]
|
|
# async runtime + HTTP server
|
|
tokio = { version = "1", features = ["full"] }
|
|
axum = { version = "0.7", features = ["macros"] }
|
|
tower = "0.5"
|
|
tower-http = { version = "0.6", features = ["limit", "trace", "cors"] }
|
|
|
|
# HTTP client to providers and to cortiq-router (rustls, no OpenSSL)
|
|
reqwest = { version = "0.12", default-features = false, features = ["json", "stream", "rustls-tls"] }
|
|
|
|
# serialization
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
toml = "0.8"
|
|
|
|
# hot-reloadable shared state + embedded admin SPA
|
|
arc-swap = "1"
|
|
rust-embed = "8"
|
|
mime_guess = "2"
|
|
|
|
# cross-platform CSPRNG for admin/key token generation (Linux/macOS/Windows)
|
|
getrandom = "0.2"
|
|
|
|
# streaming / async utils
|
|
futures = "0.3"
|
|
async-trait = "0.1"
|
|
async-stream = "0.3"
|
|
bytes = "1"
|
|
tokio-stream = "0.1"
|
|
|
|
# CLI / config
|
|
clap = { version = "4", features = ["derive"] }
|
|
|
|
# errors / logging / metrics
|
|
thiserror = "1"
|
|
anyhow = "1"
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
|
|
|
[profile.release]
|
|
lto = true
|
|
codegen-units = 1
|