jpmschweitzer/settled-reach
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files
Makefile
+24
View File
@@ -7,6 +7,7 @@ GODOT := $(shell command -v godot4 2>/dev/null || command -v godot 2>/dev/null)
pre-pr-server pre-pr-client pre-pr-content \
fixtures-client fixtures-gauntlet golden-diff golden-update \
checklist-validate checklist-generate \
build-sr-voice run-sr-voice \
perf-baseline debug-schedule \
test-ipc-fixtures test-ipc-protocol test-ipc-integration test-ipc-benchmark \
screenshot visual-movie test-visual visual-update
@@ -65,6 +66,10 @@ help:
@echo " make pre-pr-content Content-scoped pre-PR (schema + cross-ref validation)"
@echo ""
@echo " make setup-hooks Install pre-commit hooks (included in setup)"
@echo " make build-sr-voice Build sr-voice LLM inference service"
@echo " make serve-sr-voice Start sr-voice server (ARGS='--model <path>')"
@echo " make run-sr-voice Submit to sr-voice server (ARGS='generate|batch|benchmark ...')"
@echo " make stop-sr-voice Stop sr-voice server"
@echo " make debug-schedule Print bevy_ecs schedule graph (diff for PR artifacts)"
@echo ""
@echo " GODOT_VERSION=4.6 make setup Override Godot version"
@@ -344,6 +349,25 @@ test-visual:
visual-update:
@tests/run-visual --update
LIBCLANG_PATH ?= /usr/lib64/rocm/llvm/lib
BINDGEN_CLANG_ARGS ?= -I/usr/lib64/rocm/llvm/lib/clang/19/include
SR_VOICE_ENV = LIBCLANG_PATH=$(LIBCLANG_PATH) BINDGEN_EXTRA_CLANG_ARGS="$(BINDGEN_CLANG_ARGS)"
SR_VOICE_PORT ?= 8321
build-sr-voice:
cd server/sr-voice && $(SR_VOICE_ENV) cargo build --release
serve-sr-voice:
cd server/sr-voice && $(SR_VOICE_ENV) cargo run --release -- serve $(ARGS)
run-sr-voice:
cd server/sr-voice && $(SR_VOICE_ENV) cargo run --release -- $(ARGS)
stop-sr-voice:
@lsof -ti :$(SR_VOICE_PORT) | xargs -r kill 2>/dev/null || true
@echo "Stopped sr-voice on port $(SR_VOICE_PORT)"
content-ron:
cd tooling/content-converter && cargo build --release
tooling/content-converter/target/release/content-converter --input content --output content-ron --verbose