SKaiNET-developers · michalharakal · Sep 7, 2026 · Sep 7, 2026 · Sep 7, 2026 · Sep 7, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.54.1] — 2026-09-07
+
+A transformers-only release, same pattern as 0.40.2: no new engine version, still against
+**SKaiNET engine 0.54.0**. `MultiHeadAttention` becomes the first consumer of the engine's
+SKEEP-005 `Schedule`, and positional KV caches stop copying the whole prefix per layer per token.
+
 ### Added — schedule-driven attention: parallel heads, copy-free K/V (SKaiNET SKEEP-005)
 
 - **Attention heads run in parallel** (#413): `MultiHeadAttention` maps heads (or GQA groups) onto
@@ -32,7 +38,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `SKAINET_KV_CACHE=append|positional` (verified on Llama-3.2-1B, Qwen2.5-0.5B and Qwen3-1.7B
   Q8_0); `AttentionScheduleSpeedProfile` (opt-in) measures all four combinations. Docs: `docs/specs/attention-schedule.md`, the *Parallel Attention Heads via
   Schedules* explanation and the *Parallel Attention — Getting Started* tutorial.
-- Requires engine **0.54.0** (published; see below).
 
 ## [0.54.0] — 2026-09-07
 

diff --git a/README.md b/README.md
@@ -109,9 +109,18 @@ Honest status — see the project-status note at the top of this README.
 
 ## Current release
 
-The current release is **0.54.0** (against **SKaiNET 0.54.0**) — version lock-step with the engine
-continues, plus two bugs fixed on real hardware and the FunctionGemma/IREE-Android chunked-KV work
-closed out.
+The current release is **0.54.1** (against **SKaiNET 0.54.0** — a transformers-only release, same
+pattern as 0.40.2: no new engine version needed).
+
+**Attention heads run in parallel.** `MultiHeadAttention` is the first consumer of the engine's
+SKEEP-005 `Schedule`: heads (or GQA groups) map onto cores via `AttentionSchedulePolicy`
+(`Sequential` / `PerHead` / `PerKVGroup` / `Auto`), bit-identical to the sequential path.
+`KVCache.updateInPlace` returns copy-free `KVBufferView`s for positional caches instead of copying
+the whole prefix per layer per token, and `DecoderKVCacheKind.POSITIONAL` brings that to Llama and
+Qwen. Verified on Llama-3.2-1B, Qwen2.5-0.5B and Qwen3-1.7B against mainline llama.cpp.
+
+It builds on **0.54.0**, which restored version lock-step with the engine, plus two bugs fixed on
+real hardware and the FunctionGemma/IREE-Android chunked-KV work closed out.
 
 **A stateful Android KV session for FunctionGemma.** `IreeKvSession` / `IreeKvDecoder`
 (`llm-runtime/iree-android`) prefill the tool catalog once per process, snapshot the KV state, and
@@ -209,7 +218,7 @@ The recommended way to consume is via the BOM. It pins every published `skainet-
 
 ```kotlin
 dependencies {
-    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.1"))
 
     // Versions resolved from the BOM:
     implementation("sk.ainet.transformers:skainet-transformers-core")

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:0.54.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.1"))
     implementation("sk.ainet.transformers:skainet-transformers-inference-moonshine")
 }
 ----

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:0.54.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.1"))
     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:0.54.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.1"))
 
     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>0.54.0</version>
+      <version>0.54.1</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:0.54.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.1"))
     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:0.54.0"))
+    implementation(platform("sk.ainet.transformers:skainet-transformers-bom:0.54.1"))
 
     implementation("sk.ainet.transformers:skainet-transformers-runtime-kllama")
     implementation("sk.ainet.transformers:skainet-transformers-agent")

diff --git a/docs/modules/ROOT/pages/tutorials/parallel-attention-getting-started.adoc b/docs/modules/ROOT/pages/tutorials/parallel-attention-getting-started.adoc
@@ -10,8 +10,7 @@ schedule only decides where the work runs.
 
 * JDK 21+ (the JVM is the only target with a parallel schedule; others run `Schedule.Sequential`).
 * A Llama 3.2 or Qwen3 GGUF, for example `Llama-3.2-1B-Instruct-Q8_0.gguf`.
-* SKaiNET-transformers 0.54.0 or later, or — until that release — the `feature/attention-schedule`
-  branch built against the engine checkout with `-PuseLocalSkainet=true`.
+* SKaiNET-transformers 0.54.1 or later.
 
 == Step 1: Dependencies
 

diff --git a/docs/specs/attention-schedule.md b/docs/specs/attention-schedule.md
@@ -4,7 +4,7 @@
 **Depends on:** SKaiNET engine `Schedule` API — [SKEEP-005](https://skainet-developers.github.io/SKaiNET/skainet/skeep/005-schedules-structured-concurrency.html) (`sk.ainet.context.schedule`, `DirectCpuExecutionContext(schedule = …)`, `CoroutineSchedule`)
 **Issues:** transformers #412 (per-head fused attention copies the K/V prefix per layer per token), #413 (attention is single-threaded)
 **Labels:** enhancement, performance
-**Milestone:** 0.54.0 (lock-step with engine 0.54.0)
+**Milestone:** 0.54.1 (transformers-only release; engine 0.54.0)
 
 ---
 
@@ -132,9 +132,8 @@ returns `null` (→ copied path) on segment-backed data. Every override returns
 | AS-8 | vectorised inner dots, growable positional cache | follow-up |
 
 Checkpoints: CP-1 engine `Schedule` API available (SKaiNET `feature/skeep-005-schedules`);
-CP-2 transformer-core parity green; CP-3 golden gates green under every switch; CP-4 both
-repositories released as 0.54.0 in lock-step (until then: build transformers with
-`-PuseLocalSkainet=true`).
+CP-2 transformer-core parity green; CP-3 golden gates green under every switch; CP-4 engine
+0.54.0 published, transformers released as 0.54.1 on top of it.
 
 [transformers#412]: https://github.com/SKaiNET-developers/SKaiNET-transformers/issues/412
 [transformers#413]: https://github.com/SKaiNET-developers/SKaiNET-transformers/issues/413
diff --git a/gradle.properties b/gradle.properties
@@ -1,5 +1,5 @@
 GROUP=sk.ainet.transformers
-VERSION_NAME=0.54.0
+VERSION_NAME=0.54.1
 
 POM_DESCRIPTION=SKaiNET-transformers
 

diff --git a/llm-inference/gemma/README.md b/llm-inference/gemma/README.md
@@ -4,7 +4,7 @@ Reusable **Gemma** model (incl. the FunctionGemma tool-calling fine-tune) author
 a portable graph producer with **no runtime/board/Torq code**. Pair it with the runtime module below to
 decode on-device.
 
-- **Coordinate:** `sk.ainet.transformers:skainet-transformers-inference-gemma:0.54.0`
+- **Coordinate:** `sk.ainet.transformers:skainet-transformers-inference-gemma:0.54.1`
 - **Targets:** `android`, `iosArm64`, `iosSimulatorArm64`, `macosArm64`, `linuxX64`, `linuxArm64` (broadly
   portable — mobile through server).
 - **Entry point:** `gemmaNetwork()` / `GemmaNetworkLoader` (loads a GGUF, builds the DSL graph, incl. the
@@ -24,8 +24,8 @@ FunctionGemma has a one-liner facade in `…:skainet-transformers-runtime-kgemma
 
 ```kotlin
 dependencies {
-    implementation("sk.ainet.transformers:skainet-transformers-inference-gemma:0.54.0")
-    implementation("sk.ainet.transformers:skainet-transformers-runtime-gemma-iree:0.54.0") // on-device decode
+    implementation("sk.ainet.transformers:skainet-transformers-inference-gemma:0.54.1")
+    implementation("sk.ainet.transformers:skainet-transformers-runtime-gemma-iree:0.54.1") // on-device decode
 }
 ```