feat(engine): add sr-voice LLM inference service for NPC voice pipeline

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>

This commit is contained in:

jpmschweitzer

2026-03-07 15:44:37 +01:00

co-authored by

Claude Opus 4.6

parent 102b55f64a

commit 1b58d8f949

8 changed files with 1598 additions and 0 deletions

.gitignore

View File

@@ -2,6 +2,8 @@
 .cache/
 .tmp/
 server/target/
 server/sr-voice/target/
 server/models/
 tooling/content-converter/target/
 tooling/line-previewer/target/
 tooling/test-client/target/