runtime-llamacpp-v0.2.1 v1.4.4

modelscope/FunASRAug 26, 2026 → Aug 26, 20260 days between releases

Generating AI comparison

Analyzing what changed between runtime-llamacpp-v0.2.1 and v1.4.4. This page updates automatically — usually within a minute.

The Two Releases

runtime-llamacpp-v0.2.1

FunASR llama.cpp runtime v0.2.1

Aug 26, 2026· 2 months ago

Introduces prebuilt self-contained binaries for the FunASR llama.cpp runtime, supporting SenseVoice, Paraformer, and Fun-ASR-Nano models with built-in FSMN-VAD. It offers various hardware optimizations including AVX2, Vulkan, and CUDA backends to enhance performance across different platforms.

Full release notes
v1.4.4

FunASR 1.4.4

Aug 26, 2026· 2 months ago

This release focuses on major performance improvements for Realtime WebSocket concurrency and enhanced compatibility. It removes serialization locks, batches decode requests, and improves exception handling while maintaining compatibility with older PyTorch versions.

Full release notes