modelscope · LauraGPT · Aug 27, 2026 · Aug 27, 2026
diff --git a/README.md b/README.md
@@ -306,7 +306,7 @@ GPUs report compute capability 12.0 (`sm_120`) and should use the CPU package or
 build from source with `-DCMAKE_CUDA_ARCHITECTURES=120` until a dedicated CUDA
 asset is published.
 
-**Prebuilt binaries:** [Releases](https://github.com/modelscope/FunASR/releases) · [v0.2.0](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.0) · [Linux Vulkan tarball](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.0/funasr-llamacpp-linux-x64-vulkan.tar.gz) · [Windows Vulkan zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.0/funasr-llamacpp-windows-x64-vulkan.zip) · [Windows CUDA zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.0/funasr-llamacpp-windows-x64-cuda.zip) · **Download & quickstart:** [funasr.com/deploy/llama-cpp](https://www.funasr.com/en/deploy/llama-cpp.html) · **GGUF models:** [Hugging Face](https://huggingface.co/FunAudioLLM) · **Docs & benchmarks:** [runtime/llama.cpp/](./runtime/llama.cpp/)
+**Prebuilt binaries:** [Releases](https://github.com/modelscope/FunASR/releases) · [v0.2.1](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1) · [Linux Vulkan tarball](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.1/funasr-llamacpp-linux-x64-vulkan.tar.gz) · [Windows Vulkan zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.1/funasr-llamacpp-windows-x64-vulkan.zip) · [Windows CUDA zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.1/funasr-llamacpp-windows-x64-cuda.zip) · **Download & quickstart:** [funasr.com/deploy/llama-cpp](https://www.funasr.com/en/deploy/llama-cpp.html) · **GGUF models:** [Hugging Face](https://huggingface.co/FunAudioLLM) · **Docs & benchmarks:** [runtime/llama.cpp/](./runtime/llama.cpp/)
 
 [OpenAI API example →](./examples/openai_api/) · [Gradio demo →](./examples/openai_api/GRADIO.md) · [Client recipes →](./examples/openai_api/CLIENTS.md) · [JavaScript/TypeScript recipes →](./examples/openai_api/JAVASCRIPT.md) · [Kubernetes template →](./examples/openai_api/kubernetes/) · [Workflow recipes →](./examples/openai_api/WORKFLOWS.md) · [Postman collection →](./examples/openai_api/POSTMAN.md) · [OpenAPI spec →](./examples/openai_api/OPENAPI.md) · [Security guide →](./examples/openai_api/SECURITY.md) · [Deployment matrix →](./docs/deployment_matrix.md) · [Deployment docs →](./runtime/readme.md) · [Agent integration →](https://modelscope.github.io/FunASR/agent.html)
 
@@ -330,6 +330,7 @@ asset is published.
 
 ## What's new
 
+- 2026/08/27: **llama.cpp runtime v0.2.1** — Vulkan device selection now accepts matching integrated GPUs, prefers a matching discrete GPU when both are available, and otherwise falls back to the iGPU. Nine Linux, macOS, and Windows archives were rebuilt and verified with published SHA-256 values. Radeon 780M still needs reporter hardware confirmation; the separate RX 9070 XT `0xC0000005` initialization crash is not claimed fixed. [Download matrix & quickstart ->](https://www.funasr.com/en/deploy/llama-cpp.html) · [Release ->](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1)
 - 2026/08/26: **v1.4.4 on PyPI** — realtime WebSocket decoding now batches compatible sessions instead of serializing every connection behind one process-wide lock. On the H100 regression workload, 12-client STOP p95 fell from 19.8 s to 0.4 s and 16-client aggregate throughput rose from 8.6x to 13.2x, with no client errors. This hotfix also restores compatibility with PyTorch releases that do not expose `torch.amp` and raises real runtime-binding exceptions. Upgrade with `python -m pip install -U "funasr==1.4.4"`. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.4)
 - 2026/08/21: **v1.4.3 on PyPI** — `AutoModel(vad_model="silero-vad")` now offers an optional Silero VAD adapter with millisecond segments, configurable thresholds, 8/16 kHz input, ONNX mode, and bounded segment lengths. Upgrade with `python -m pip install -U "funasr==1.4.3"`; enable the adapter with `python -m pip install -U "funasr[silero]==1.4.3"`. Speaker diarization with a known speaker count now routes large embedding sets through fixed-K clustering instead of memory-heavy dense spectral clustering. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.3)
 - 2026/08/14: **v1.4.2 on PyPI** — punctuation-aware sentence alignment now preserves subtitle segmentation when a punctuation token boundary splits a timestamped ASR word. Distributed training now synchronizes DDP/FSDP gradients on the final microbatch of each accumulation window and initializes DeepSpeed/FSDP mode from the resolved configuration. The tagged source also includes llama.cpp SRT output and the v0.2.0 AMD Vulkan submission updates. Install with `python -m pip install -U "funasr==1.4.2"`. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.2)

diff --git a/README_ja.md b/README_ja.md
@@ -99,6 +99,7 @@ Whisper は単一モデルですが、**FunASR はツールキット**です—
 
 ## 最新情報
 
+- 2026/08/27：**llama.cpp runtime v0.2.1** — Vulkan のデバイス選択が一致する統合 GPU を受け入れ、一致する discrete GPU があればそちらを優先し、なければ iGPU にフォールバックするようになりました。SHA-256 を公開した Linux、macOS、Windows 向け 9 archive を再構築・検証済みです。Radeon 780M は報告者の実機確認待ちで、別件の RX 9070 XT `0xC0000005` 初期化 crash は修正済みとはしていません。[ダウンロード一覧と quickstart →](https://www.funasr.com/en/deploy/llama-cpp.html) · [Release →](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1)
 - 2026/08/26：**v1.4.4 を PyPI に公開** — realtime WebSocket decode は、全 connection を 1 つの process-wide lock で直列化せず、互換性のある session を batch 処理するようになりました。H100 regression workload では、12 client の STOP p95 が 19.8 秒から 0.4 秒に短縮され、16 client の aggregate throughput は 8.6x から 13.2x に向上し、client error は 0 件でした。この hotfix は `torch.amp` を持たない PyTorch release との互換性も復元し、runtime binding から実際の例外を送出します。更新：`python -m pip install -U "funasr==1.4.4"`。[Release →](https://github.com/modelscope/FunASR/releases/tag/v1.4.4)
 - 2026/08/21：**v1.4.3 を PyPI に公開** — `AutoModel(vad_model="silero-vad")` で任意の Silero VAD アダプターを利用でき、ミリ秒単位の区間、しきい値、8/16 kHz 入力、ONNX mode、最大区間長を設定できます。更新：`python -m pip install -U "funasr==1.4.3"`。アダプターの有効化：`python -m pip install -U "funasr[silero]==1.4.3"`。話者数が既知の話者ダイアライゼーションは、大規模 embedding をメモリ負荷の高い密なスペクトラルクラスタリングではなく fixed-K クラスタリングで処理します。[Release →](https://github.com/modelscope/FunASR/releases/tag/v1.4.3)
 - 2026/08/14：**v1.4.2 を PyPI に公開** — 句読点モデルの token 境界がタイムスタンプ付き ASR 単語の内部にある場合でも、文アラインメントが字幕分割を正しく保持するようになりました。分散学習では、各勾配累積 window の最後の microbatch で DDP/FSDP 勾配を同期し、解決済み設定から DeepSpeed/FSDP mode を初期化します。対応する GitHub ソース tag には llama.cpp SRT 出力と v0.2.0 の AMD Vulkan submission 更新も含まれます。インストール：`python -m pip install -U "funasr==1.4.2"`。[Release →](https://github.com/modelscope/FunASR/releases/tag/v1.4.2)

diff --git a/README_ko.md b/README_ko.md
@@ -99,6 +99,7 @@ Whisper는 단일 모델이지만, **FunASR는 툴킷**입니다. 용도에 맞
 
 ## 최신 소식
 
+- 2026/08/27: **llama.cpp runtime v0.2.1** — Vulkan device 선택이 일치하는 integrated GPU를 허용하며, 일치하는 discrete GPU가 함께 있으면 이를 우선하고 없으면 iGPU로 fallback합니다. SHA-256을 공개한 Linux, macOS, Windows용 archive 9개를 다시 빌드하고 검증했습니다. Radeon 780M은 제보자의 실제 하드웨어 확인이 필요하며, 별도 RX 9070 XT `0xC0000005` 초기화 crash는 수정됐다고 주장하지 않습니다. [다운로드 목록 및 quickstart →](https://www.funasr.com/en/deploy/llama-cpp.html) · [Release →](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1)
 - 2026/08/26: **v1.4.4 PyPI 공개** — realtime WebSocket decode가 모든 connection을 하나의 process-wide lock으로 직렬화하지 않고 호환되는 session을 batch 처리합니다. H100 regression workload에서 12-client STOP p95는 19.8초에서 0.4초로 줄었고, 16-client aggregate throughput은 8.6x에서 13.2x로 향상됐으며 client error는 0건이었습니다. 이 hotfix는 `torch.amp`가 없는 PyTorch release와의 호환성도 복원하고 runtime binding에서 실제 예외를 발생시킵니다. 업데이트: `python -m pip install -U "funasr==1.4.4"`. [Release →](https://github.com/modelscope/FunASR/releases/tag/v1.4.4)
 - 2026/08/21: **v1.4.3 PyPI 공개** — `AutoModel(vad_model="silero-vad")`에서 선택형 Silero VAD adapter를 사용할 수 있으며, 밀리초 단위 구간, threshold, 8/16 kHz 입력, ONNX mode, 최대 구간 길이를 지원합니다. 업데이트: `python -m pip install -U "funasr==1.4.3"`. Adapter 활성화: `python -m pip install -U "funasr[silero]==1.4.3"`. 화자 수를 알고 있는 speaker diarization은 대규모 embedding을 메모리 사용량이 큰 dense spectral clustering 대신 fixed-K clustering으로 처리합니다. [Release →](https://github.com/modelscope/FunASR/releases/tag/v1.4.3)
 - 2026/08/14: **v1.4.2 PyPI 공개** — 문장부호 모델의 token 경계가 타임스탬프가 있는 ASR 단어 내부에 놓여도 문장 정렬이 올바른 자막 분할을 유지합니다. 분산 학습은 각 gradient accumulation window의 마지막 microbatch에서 DDP/FSDP gradient를 동기화하고, 해석된 설정에서 DeepSpeed/FSDP mode를 초기화합니다. 해당 GitHub 소스 tag에는 llama.cpp SRT 출력과 v0.2.0 AMD Vulkan submission 업데이트도 포함됩니다. 설치: `python -m pip install -U "funasr==1.4.2"`. [Release →](https://github.com/modelscope/FunASR/releases/tag/v1.4.2)

diff --git a/README_zh.md b/README_zh.md
@@ -149,6 +149,7 @@ Whisper 是单个模型，**FunASR 是一个工具箱**——按场景挑模型
 
 ## 最新动态
 
+- 2026/08/27：**llama.cpp runtime v0.2.1** — Vulkan 设备选择现在接受匹配的集成 GPU；同时存在匹配独显时优先独显，否则回退到核显。九个 Linux、macOS 与 Windows 压缩包已重新构建并通过公开 SHA-256 复核。Radeon 780M 仍需报告者实机确认；单独的 RX 9070 XT `0xC0000005` 初始化崩溃不在本次修复声明内。[下载矩阵与快速开始 →](https://www.funasr.com/deploy/llama-cpp.html) · [发布页 →](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1)
 - 2026/08/26：**v1.4.4 已发布到 PyPI** — 实时 WebSocket 解码会对兼容会话进行批处理，不再让所有连接排队经过同一个进程级锁。在 H100 回归负载下，12 路 STOP p95 从 19.8 秒降至 0.4 秒，16 路聚合吞吐从 8.6x 提升到 13.2x，且客户端零错误。本热修复同时兼容不提供 `torch.amp` 的 PyTorch 版本，并让运行时绑定抛出真实异常。升级命令：`python -m pip install -U "funasr==1.4.4"`。[发布页 →](https://github.com/modelscope/FunASR/releases/tag/v1.4.4)
 - 2026/08/21：**v1.4.3 已发布到 PyPI** — `AutoModel(vad_model="silero-vad")` 现可选用 Silero VAD 适配器，返回毫秒级片段，并支持阈值、8/16 kHz 输入、ONNX 模式和最长片段限制。基础升级命令：`python -m pip install -U "funasr==1.4.3"`；启用该适配器：`python -m pip install -U "funasr[silero]==1.4.3"`。已知说话人数的说话人分离在大规模 embedding 输入下改用固定 K 聚类，避免内存开销较高的稠密谱聚类。[发布页 →](https://github.com/modelscope/FunASR/releases/tag/v1.4.3)
 - 2026/08/14：**v1.4.2 已发布到 PyPI** — 标点模型的 token 边界落在带时间戳的 ASR 词内部时，句子对齐现在仍能保留正确的字幕分段。分布式训练会在每个梯度累积窗口的最后一个 microbatch 同步 DDP/FSDP 梯度，并从解析后的配置正确初始化 DeepSpeed/FSDP 模式。对应 GitHub 源码 tag 同时包含 llama.cpp SRT 输出和 v0.2.0 AMD Vulkan submission 更新。安装命令：`python -m pip install -U "funasr==1.4.2"`。[发布页 →](https://github.com/modelscope/FunASR/releases/tag/v1.4.2)
@@ -359,7 +360,7 @@ Windows Vulkan ZIP 使用显卡驱动提供的系统 Vulkan loader，不需要
 compute capability 12.0（`sm_120`），在专用 CUDA 产物发布前，请使用 CPU 包，或从
 源码构建并设置 `-DCMAKE_CUDA_ARCHITECTURES=120`。
 
-**预编译二进制：** [Releases](https://github.com/modelscope/FunASR/releases) · [v0.2.0](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.0) · [Linux Vulkan tarball](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.0/funasr-llamacpp-linux-x64-vulkan.tar.gz) · [Windows Vulkan zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.0/funasr-llamacpp-windows-x64-vulkan.zip) · [Windows CUDA zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.0/funasr-llamacpp-windows-x64-cuda.zip) · **下载与快速开始：** [funasr.com/deploy/llama-cpp](https://www.funasr.com/deploy/llama-cpp.html) · **GGUF 模型：** [Hugging Face](https://huggingface.co/FunAudioLLM) · **文档与评测：** [runtime/llama.cpp/](./runtime/llama.cpp/)
+**预编译二进制：** [Releases](https://github.com/modelscope/FunASR/releases) · [v0.2.1](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1) · [Linux Vulkan tarball](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.1/funasr-llamacpp-linux-x64-vulkan.tar.gz) · [Windows Vulkan zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.1/funasr-llamacpp-windows-x64-vulkan.zip) · [Windows CUDA zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.2.1/funasr-llamacpp-windows-x64-cuda.zip) · **下载与快速开始：** [funasr.com/deploy/llama-cpp](https://www.funasr.com/deploy/llama-cpp.html) · **GGUF 模型：** [Hugging Face](https://huggingface.co/FunAudioLLM) · **文档与评测：** [runtime/llama.cpp/](./runtime/llama.cpp/)
 
 [OpenAI API 示例 →](./examples/openai_api/README_zh.md) · [Gradio Demo →](./examples/openai_api/GRADIO_zh.md) · [客户端配方 →](./examples/openai_api/CLIENTS.md) · [JavaScript/TypeScript 配方 →](./examples/openai_api/JAVASCRIPT_zh.md) · [Kubernetes 模板 →](./examples/openai_api/kubernetes/README_zh.md) · [工作流配方 →](./examples/openai_api/WORKFLOWS_zh.md) · [Postman 集合 →](./examples/openai_api/POSTMAN_zh.md) · [OpenAPI 规范 →](./examples/openai_api/OPENAPI_zh.md) · [安全指南 →](./examples/openai_api/SECURITY_zh.md) · [部署选型 →](./docs/deployment_matrix_zh.md) · [部署文档 →](./runtime/readme_cn.md) · [Agent 集成 →](https://modelscope.github.io/FunASR/agent.html)
 

diff --git a/runtime/llama.cpp/tests/test_download_funasr_model.sh b/runtime/llama.cpp/tests/test_download_funasr_model.sh
@@ -170,8 +170,8 @@ assert_readme_quickstart() {
     printf 'non-portable Releases link in %s\n' "$readme" >&2
     exit 1
   fi
-  if ! grep -F 'runtime-llamacpp-v0.2.0' <<<"$section" >/dev/null; then
-    printf 'missing current runtime v0.2.0 link in %s\n' "$readme" >&2
+  if ! grep -F 'runtime-llamacpp-v0.2.1' <<<"$section" >/dev/null; then
+    printf 'missing current runtime v0.2.1 link in %s\n' "$readme" >&2
     exit 1
   fi
   if ! grep -F 'funasr-llamacpp-linux-x64-vulkan' <<<"$section" >/dev/null; then

diff --git a/tests/test_docs_funasr_install_commands.py b/tests/test_docs_funasr_install_commands.py
@@ -343,7 +343,7 @@ def test_top_level_readmes_surface_current_release_and_edge_runtime():
     for name, text in readmes.items():
         assert 'python -m pip install -U "funasr==1.4.1"' in text, name
         assert "https://github.com/modelscope/FunASR/releases/tag/v1.4.1" in text, name
-        assert "runtime-llamacpp-v0.2.0" in text, name
+        assert "runtime-llamacpp-v0.2.1" in text, name
 
     assert "https://www.funasr.com/en/deploy/llama-cpp.html" in readmes["README.md"]
     assert "https://www.funasr.com/deploy/llama-cpp.html" in readmes["README_zh.md"]
@@ -358,7 +358,7 @@ def test_top_level_readmes_surface_current_release_and_edge_runtime():
             "funasr-llamacpp-windows-x64-cuda.zip",
         ):
             assert (
-                f"releases/download/runtime-llamacpp-v0.2.0/{asset}" in text
+                f"releases/download/runtime-llamacpp-v0.2.1/{asset}" in text
             ), name
         assert "releases/download/runtime-llamacpp-v0.1.9/" not in text, name