live: heartbeat sync 2026-10-18T16:47:59-07:00 (Refs #11)

agent/memories/sharpshooter/wt-20261017-173221-6d1fc1f-cyy12v5yf03k/architecture.md

@@ -0,0 +1,4 @@
+## Model Format
+
+- **Quantization** — established across all LLM endpoints; each service (radiance, halogen-flash-server, llama.cpp) applies its own quantization scheme as part of the runtime.
+- **Qwen3.8-Flash-Next `.rad`** — radiance container uses `.rad` format natively; the format encodes routed experts as 4-bit codes into a 16-level non-uniform codebook (128-pt Walsh–Hadamard rotation, GPTQ on calibration + 3 coordinate-descent sweeps, E4M3 scales per 64 weights), with 10 whole bf16-protected experts/layer, int8 W8A8 trunk/lm_head, fp8 HC mixtures, and fp8 fixed-scale PLE n-gram.