michalharakal · Nov 7, 2026 · Nov 7, 2026 · Nov 7, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,17 @@ requiring an engine release. `0.57.1` against engine `0.57.0` is such a release.
 The format roughly follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.64.1] — 2026-11-07
+
+Against engine **0.63.0**. A packaging fix: Maven Central refused the 0.64.0 deployment, so **0.64.0 was never
+published** and its content (below) ships with this release.
+
+### Fixed
+
+- `skainet-transformers-inference-lfm2` imports the BOM as `api`: it declares `skainet-lang-core` and
+  `skainet-backend-cpu` as `api` dependencies, and with the BOM only as `implementation` its POM listed both without a
+  version, which Central rejects.
+
 ## [0.64.0] — 2026-11-06
 
 Against engine **0.63.0** (block-quantized weights through StableHLO export: SKaiNET#1478 and SKaiNET#1479, plus

diff --git a/README.md b/README.md
@@ -115,7 +115,7 @@ Honest status — see the project-status note at the top of this README.
 
 ## Current release
 
-The current release is **0.64.0**, against **SKaiNET 0.63.0**: `DecodeStepExport` (`llm-core`) traces one single-token step of any KV-cache decoder with a static past and keeps Q8_0 / Q4_0 weights packed for the engine's block-quant matmul fusion, so FunctionGemma 270M's decode step compiles to one dispatch on the Torq NPU of an SL2610 (162 ms per step, same top-1 as the f32 reference); the with-past types (`RopeCosSin`, `ChunkContext`, `KvStepOutput`) are shared by Gemma and the generic KV decoder in `sk.ainet.lang.nn.dsl.decoder`. LFM2 arrives as `llm-inference:lfm2` (dense hybrid short-conv + GQA model, verified checkpoint loading, fixed-shape StableHLO export) and the `llm-runtime:klfm2` chat frontend. 0.63.3 let the streaming Moonshine runtime hand the decoder to an external native library too (`ext:<library.so>|<model dir>` as the prefill path), so with 0.63.2's external encoder the whole model can run on an accelerator outside IREE while the runtime keeps the streaming loop, greedy decoding and its guards. 0.63.2 handed the encoder side to an external library (`ext:` as the encoder path) 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).
+The current release is **0.64.1**, against **SKaiNET 0.63.0**: a packaging fix: Maven Central refused 0.64.0 (the `skainet-transformers-inference-lfm2` POM lacked dependency versions), so 0.64.0 was never published and its content ships here. `DecodeStepExport` (`llm-core`) traces one single-token step of any KV-cache decoder with a static past and keeps Q8_0 / Q4_0 weights packed for the engine's block-quant matmul fusion, so FunctionGemma 270M's decode step compiles to one dispatch on the Torq NPU of an SL2610 (162 ms per step, same top-1 as the f32 reference); the with-past types (`RopeCosSin`, `ChunkContext`, `KvStepOutput`) are shared by Gemma and the generic KV decoder in `sk.ainet.lang.nn.dsl.decoder`. LFM2 arrives as `llm-inference:lfm2` (dense hybrid short-conv + GQA model, verified checkpoint loading, fixed-shape StableHLO export) and the `llm-runtime:klfm2` chat frontend. 0.63.3 let the streaming Moonshine runtime hand the decoder to an external native library too (`ext:<library.so>|<model dir>` as the prefill path), so with 0.63.2's external encoder the whole model can run on an accelerator outside IREE while the runtime keeps the streaming loop, greedy decoding and its guards. 0.63.2 handed the encoder side to an external library (`ext:` as the encoder path) 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).
 
@@ -305,7 +305,7 @@ The recommended way to consume is via the BOM. It pins every published `skainet-
 
 ```kotlin
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
 
     // 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:0.64.0"))
+    exportTool(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
     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:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
     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:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
     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:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
     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:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
 
     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>0.64.0</version>
+      <version>0.64.1</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:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
     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:0.64.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.64.1"))
 
     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=0.64.0
+VERSION_NAME=0.64.1
 
 POM_DESCRIPTION=SKaiNET-transformers
 

diff --git a/llm-inference/lfm2/build.gradle.kts b/llm-inference/lfm2/build.gradle.kts
@@ -17,7 +17,8 @@ kotlin {
     jvm()
     sourceSets {
         commonMain.dependencies {
-            implementation(project.dependencies.platform(project(":llm-bom")))
+            // api, not implementation: the api dependencies below take their versions from it in the POM.
+            api(project.dependencies.platform(project(":llm-bom")))
             api(libs.skainet.lang.core)
             api(libs.skainet.backend.cpu)
             api(libs.kotlinx.serialization.json)