jpmschweitzerandClaude Opus 4.6
1b58d8f949
Standalone Rust crate wrapping llama-cpp-2 for GGUF model inference. Persistent HTTP server architecture — model loaded once, requests processed sequentially, zero CPU contention by construction. Subcommands: serve (load model, listen), generate (single prompt), batch (JSONL), benchmark (5-run average). Makefile targets for build/serve/run/stop workflow. Spike 1 validated: Gemma 2B Q4_K_M at ~16 t/s CPU, 4 cultures tested (Krenn, Ireland, Shek'na, Aranthi), composition-engine oath injection mechanism proven. GO for Spike 2. Refs: D-138, #639 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
21 lines
402 B
TOML
21 lines
402 B
TOML
[package]
|
|
name = "sr-voice"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
|
|
[dependencies]
|
|
llama-cpp-2 = "0.1"
|
|
clap = { version = "4", features = ["derive"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
thiserror = "2"
|
|
tiny_http = "0.12"
|
|
ureq = "3"
|
|
|
|
[features]
|
|
default = []
|
|
metal = ["llama-cpp-2/metal"]
|
|
vulkan = ["llama-cpp-2/vulkan"]
|
|
cuda = ["llama-cpp-2/cuda"]
|
|
rocm = ["llama-cpp-2/rocm"]
|