Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

docs(runtime): mention Vulkan asset in release notes

zhifu gaoc7f6edb9e68b
diff --git a/.github/workflows/build-llamacpp-binaries.yml b/.github/workflows/build-llamacpp-binaries.yml
index 342001d0e..23e4b6742 100644
--- a/.github/workflows/build-llamacpp-binaries.yml
+++ b/.github/workflows/build-llamacpp-binaries.yml
@@ -209,4 +209,4 @@ jobs:
gh release create "$tag" dist/* \
--repo "${{ github.repository }}" \
--title "FunASR llama.cpp runtime $version" \
- --notes "Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime: SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD. Download the default quantized model with \`bash download-funasr-model.sh <sensevoice|paraformer|nano>\` (the helper requires the Hugging Face CLI: \`pip install -U huggingface_hub\`), then run \`llama-funasr-cli\` / \`llama-funasr-sensevoice\` / \`llama-funasr-paraformer\`. Use the default x64 asset for maximum CPU compatibility; use the x64-avx2 asset on CPUs with AVX2/FMA/F16C/BMI2 for higher throughput. The Windows CUDA asset is \`windows-x64-cuda\`; it requires an NVIDIA driver compatible with the CUDA Toolkit version configured by the release workflow, targets CUDA architecture 86, and enables SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend cuda\`. Build from source for other GPU architectures. No Python ASR runtime or local build is required. Docs: $docs"
+ --notes "Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime: SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD. Download the default quantized model with \`bash download-funasr-model.sh <sensevoice|paraformer|nano>\` (the helper requires the Hugging Face CLI: \`pip install -U huggingface_hub\`), then run \`llama-funasr-cli\` / \`llama-funasr-sensevoice\` / \`llama-funasr-paraformer\`. Use the default x64 asset for maximum CPU compatibility; use the x64-avx2 asset on CPUs with AVX2/FMA/F16C/BMI2 for higher throughput. The Linux Vulkan asset is \`linux-x64-vulkan\`; it requires a working Vulkan driver/ICD and enables SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend vulkan\`. Build from source with \`-DGGML_VULKAN=ON\` to validate distro-specific GPU stacks. The Windows CUDA asset is \`windows-x64-cuda\`; it requires an NVIDIA driver compatible with the CUDA Toolkit version configured by the release workflow, targets CUDA architecture 86, and enables SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend cuda\`. Build from source for other GPU architectures. No Python ASR runtime or local build is required. Docs: $docs"
diff --git a/runtime/llama.cpp/tests/test_release_workflow.py b/runtime/llama.cpp/tests/test_release_workflow.py
index 06e87a3be..8b900722c 100644
--- a/runtime/llama.cpp/tests/test_release_workflow.py
+++ b/runtime/llama.cpp/tests/test_release_workflow.py
@@ -70,6 +70,15 @@ def test_release_notes_explain_vulkan_linux_asset():
assert "GGML_VULKAN=ON" in readme
+
+def test_github_release_notes_mention_vulkan_asset():
+ workflow = WORKFLOW.read_text(encoding="utf-8")
+ release_notes = workflow.split('--notes "', maxsplit=1)[1]
+
+ assert "linux-x64-vulkan" in release_notes
+ assert "--backend vulkan" in release_notes
+ assert "GGML_VULKAN=ON" in release_notes
+
def test_readme_documents_lightweight_http_server():
readme = (ROOT / "runtime" / "llama.cpp" / "README.md").read_text(encoding="utf-8")