michalharakal · Oct 27, 2026 · Oct 27, 2026 · Oct 27, 2026 · Oct 27, 2026 · Oct 27, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.63.2] — 2026-10-27
+
+Against engine **0.62.0**, transformers-only and additive. The Android runtime (`runtime-iree-android`) gains an
+external-encoder hook for streaming Moonshine; it still depends on nothing but the Kotlin standard library.
+
+### Added
+
+- **Moonshine streaming: external encoder hook** (`moonshine_stream_jni.c`, `libskainet_moonshine_stream.so` both
+  ABIs). An encoder path of the form `ext:<library.so>|<model dir>` replaces the frontend, encoder and adapter graphs
+  with a native library loaded by `dlopen` that exports `moonshine_ext_encoder()` (ABI 1: one whole window of audio
+  in, the window's 64 memory rows out). An accelerator outside IREE can then run the encoder side while the decoder
+  stays on the IREE device (Vulkan or CPU). A bare library name resolves among the app's own native libraries. Without
+  the prefix nothing changes; `IreeMoonshineStream` passes the path through, so the Kotlin API is unchanged.
+  Checked on an arm32 Mali device over 444 German commands with an external encoder: 13.1 % WER against 13.9 % for
+  the all-Vulkan path from the same library.
+- `native/moonshine_stream_check.c`: `MOONSHINE_ENC` replaces the encoder path (e.g. an `ext:` encoder).
+
 ## [0.63.1] — 2026-10-22
 
 Against engine **0.62.0**, transformers-only and additive. The Android runtime (`runtime-iree-android`) gains the

diff --git a/README.md b/README.md
@@ -113,7 +113,7 @@ Honest status — see the project-status note at the top of this README.
 
 ## Current release
 
-The current release is **0.63.1**, against **SKaiNET 0.62.0**: the streaming Moonshine runtime gains an incremental frontend (an optional `frontend_step.vmfb` takes most of the frontend out of the end-of-utterance flush, transcripts unchanged) and `IreeModuleRunner` runs one compiled IREE module on Android. 0.63.0 brought expert heads and routing for Laya — a decision head fine-tuned on top of the frozen encoder (`expert.safetensors` + `expert.json`) loads on its own with `LayaExpertLoader`, any number of heads share one encoder pass per question (`LayaDecisionModel.logitsFrom`), `LayaRouterSpec` + `LayaMixtureAgent` route a request by asking the base head what kind of text it is, and `LayaMixtureDecisionAdapter` puts the mixture behind the typed decision contract; verified against the published layaMOE evaluation. The ModernBERT-large `laya-typed-decisions` checkpoint loads (`position_embedding_type: absolute`). The whisper StableHLO export ships as `WhisperExportCli`. Engine 0.62.0 brings the JVM ↔ Kotlin/Wasm parity: every kernel on the wasm tier, resident activations, fused attention / norms / softmax, browser IO parity. The Laya Q8_0 lane on the desktop JVM with the native provider needs engine 0.62.1 (SKaiNET #1436).
+The current release is **0.63.2**, against **SKaiNET 0.62.0**: the streaming Moonshine runtime can hand the encoder side to an external native library (`ext:<library.so>|<model dir>` as the encoder path), so an accelerator outside IREE runs it while the decoder stays on the IREE device. 0.63.1 gave the streaming Moonshine runtime an incremental frontend (an optional `frontend_step.vmfb` takes most of the frontend out of the end-of-utterance flush, transcripts unchanged) and `IreeModuleRunner` runs one compiled IREE module on Android. 0.63.0 brought expert heads and routing for Laya — a decision head fine-tuned on top of the frozen encoder (`expert.safetensors` + `expert.json`) loads on its own with `LayaExpertLoader`, any number of heads share one encoder pass per question (`LayaDecisionModel.logitsFrom`), `LayaRouterSpec` + `LayaMixtureAgent` route a request by asking the base head what kind of text it is, and `LayaMixtureDecisionAdapter` puts the mixture behind the typed decision contract; verified against the published layaMOE evaluation. The ModernBERT-large `laya-typed-decisions` checkpoint loads (`position_embedding_type: absolute`). The whisper StableHLO export ships as `WhisperExportCli`. Engine 0.62.0 brings the JVM ↔ Kotlin/Wasm parity: every kernel on the wasm tier, resident activations, fused attention / norms / softmax, browser IO parity. The Laya Q8_0 lane on the desktop JVM with the native provider needs engine 0.62.1 (SKaiNET #1436).
 
 It builds on **0.62.2**, against **SKaiNET 0.61.0**: a transformers-only fix, the Android runtime's streaming Moonshine libraries are rebuilt with the utterance-start fix (#500; 0.62.0 and 0.62.1 packed the old build, which garbles transcripts on device). It builds on **0.62.1**, a transformers-only fix on 0.62.0, whose JVM `LayaModelLoader.load(directory, …)` had become an extension function that existing callers did not import; it is a member again (`@JvmOverloads`, so Java callers keep the 0.61 signature).
 
@@ -303,7 +303,7 @@ The recommended way to consume is via the BOM. It pins every published `skainet-
 
 ```kotlin
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
 
     // Versions resolved from the BOM:
     implementation("sk.ainet.transformers:skainet-transformers-core")

diff --git a/docs/modules/ROOT/pages/how-to/export-moonshine-v2-streaming.adoc b/docs/modules/ROOT/pages/how-to/export-moonshine-v2-streaming.adoc
@@ -32,7 +32,7 @@ From your own build, resolve the published module and run its main class:
 ----
 val exportTool by configurations.creating
 dependencies {
-    exportTool(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    exportTool(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
     exportTool("sk.ainet.transformers:skainet-transformers-inference-moonshine")
 }
 tasks.register<JavaExec>("exportMoonshine") {

diff --git a/docs/modules/ROOT/pages/reference/moonshine-encoder.adoc b/docs/modules/ROOT/pages/reference/moonshine-encoder.adoc
@@ -24,7 +24,7 @@ a DSL decoder is future work.
 [source,kotlin]
 ----
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
     implementation("sk.ainet.transformers:skainet-transformers-inference-moonshine")
 }
 ----

diff --git a/docs/modules/ROOT/pages/reference/typed-decisions.adoc b/docs/modules/ROOT/pages/reference/typed-decisions.adoc
@@ -12,7 +12,7 @@ below put that on the JVM path with the same contract for every model.
 [source,kotlin]
 ----
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
     implementation("sk.ainet.transformers:skainet-transformers-decisions-api")      // the contract, no engine dependency
     implementation("sk.ainet.transformers:skainet-transformers-decisions-runtime")  // validation + acceptance policy
     implementation("sk.ainet.transformers:skainet-transformers-inference-laya")     // Laya as a DecisionAdapter

diff --git a/docs/modules/ROOT/pages/tutorials/android-getting-started.adoc b/docs/modules/ROOT/pages/tutorials/android-getting-started.adoc
@@ -55,7 +55,7 @@ dependencies {
     // self-registers it on ART at process start — nothing to call.
     runtimeOnly("sk.ainet.core:skainet-backend-jni-cpu")
 
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
     implementation("sk.ainet.transformers:skainet-transformers-core")
     implementation("sk.ainet.transformers:skainet-transformers-runtime-kllama")
     implementation("sk.ainet.transformers:skainet-transformers-inference-llama")

diff --git a/docs/modules/ROOT/pages/tutorials/getting-started-java.adoc b/docs/modules/ROOT/pages/tutorials/getting-started-java.adoc
@@ -25,7 +25,7 @@ In your `build.gradle.kts`:
 [source,kotlin]
 ----
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
 
     implementation("sk.ainet.transformers:skainet-transformers-runtime-kllama")
     implementation("sk.ainet.transformers:skainet-transformers-agent")
@@ -41,7 +41,7 @@ Or in Maven (Maven needs the `-jvm` classifier suffix on platform artifacts):
     <dependency>
       <groupId>sk.ainet.transformers</groupId>
       <artifactId>skainet-transformers-bom</artifactId>
-      <version>0.63.1</version>
+      <version>0.63.2</version>
       <type>pom</type>
       <scope>import</scope>
     </dependency>

diff --git a/docs/modules/ROOT/pages/tutorials/getting-started-leaf.adoc b/docs/modules/ROOT/pages/tutorials/getting-started-leaf.adoc
@@ -34,7 +34,7 @@ encoder output to the advertised dimensionality. The runtime applies it automati
 [source,kotlin]
 ----
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
     implementation("sk.ainet.transformers:skainet-transformers-providers")
 }
 ----

diff --git a/docs/modules/ROOT/pages/tutorials/llama3-tool-calling.adoc b/docs/modules/ROOT/pages/tutorials/llama3-tool-calling.adoc
@@ -52,7 +52,7 @@ The pieces you need live in three modules:
 [source,kotlin]
 ----
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.1"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.63.2"))
 
     implementation("sk.ainet.transformers:skainet-transformers-runtime-kllama")
     implementation("sk.ainet.transformers:skainet-transformers-agent")

diff --git a/gradle.properties b/gradle.properties
@@ -1,5 +1,5 @@
 GROUP=sk.ainet.transformers
-VERSION_NAME=0.63.1
+VERSION_NAME=0.63.2
 
 POM_DESCRIPTION=SKaiNET-transformers
 

diff --git a/llm-runtime/iree-android/native/moonshine_stream_check.c b/llm-runtime/iree-android/native/moonshine_stream_check.c
@@ -11,6 +11,7 @@
  *                frontend_step.vmfb when the library should use the incremental frontend
  *     pcm        headerless little-endian s16 mono 16 kHz; a directory = every *.pcm in it, name order
  *     --fast     feed without pacing (timings then no longer resemble a live stream)
+ *   MOONSHINE_ENC (env) replaces the encoder path, e.g. "ext:<lib.so>|<dir>" for an external encoder
  *
  * Build (same image as the library):
  *   docker run --rm -v "$PWD/native":/src -w /src --entrypoint sh skainet/iree-android:3.11.0 -c \
@@ -77,6 +78,7 @@ int main(int argc, char** argv) {
   const char* names[] = {"frontend.vmfb", "encoder.vmfb", "adapter.vmfb", "prefill.vmfb", "step.vmfb", "params.irpa", "vocab.bin", "dec_embed.bin"};
   static char p[8][1024];
   for (int i = 0; i < 8; ++i) snprintf(p[i], sizeof p[i], "%s/%s", argv[3], names[i]);
+  if (getenv("MOONSHINE_ENC")) snprintf(p[1], sizeof p[1], "%s", getenv("MOONSHINE_ENC"));
   double t0 = now_ms();
   jlong h = create(env, NULL, (jstring)argv[2], (jstring)p[0], (jstring)p[1], (jstring)p[2], (jstring)p[3], (jstring)p[4], (jstring)p[5], (jstring)p[6], (jstring)p[7]);
   if (!h) { fprintf(stderr, "nativeCreate failed\n"); return 4; }