Card: v0.5.1 server latency (ORT 1.29); model unchanged

README.md

@@ -40,7 +40,8 @@ curl -s http://127.0.0.1:21118/v1/systemone -d '{
 
 Each answer has `probabilities` and a `confidence`; `noul` gives P(true), `choice` the picked key, `score` the
 expected level. The container also serves a live dashboard on `/` and runnable examples on `/recipes`.
-Prefer a plain binary? macOS, Linux and Windows builds are on the release page.
+Prefer a plain binary? macOS (Apple Silicon), Linux and Windows builds of the v0.5.1 server (ONNX Runtime 1.29)
+are on the [release page](https://github.com/muthuishere/openjevx/releases/latest).
 
 ## Or in Python
 
@@ -80,10 +81,13 @@ The model folder on the Go server, on CPU. The gate sets share **no state** with
 | Rule-checking basics (300) | 94.7% | 94.3% | 3.7% |
 
 **Known miss:** confidently wrong is 3.0–3.7% on the basics gates, against our 2% target. It was accepted for this
-release; the fix is planned for v0.5.1. The rest of the gate (held-out test sets, logs gate, 13 fundamentals) is
+release; the fix is planned for the next model release. The rest of the gate (held-out test sets, logs gate, 13 fundamentals) is
 still being scored and will be added here.
 
-**Benchmarks:** coming in a follow-up.
+**Latency** (v0.5.1 server, ONNX Runtime 1.29, CPU only, Apple M5 Pro, p50 end to end): 22 ms for a short
+request (36 tokens), 85 ms for a typical one (164 tokens), 540 ms near the 1024-token limit. Cold start is about
+1 s once per process. ONNX Runtime 1.29 or newer is needed for this speed: it keeps the 8-bit weights 8-bit
+(`MatMulNBits`); in Python, `pip install -U onnxruntime`.
 
 ## What v0.5.0 was trained on