v1.3.13

sxyazi/yaziv1.3.13Jun 22, 2026by github-actions[bot]

AI Summary

This release focuses on documentation improvements for the llama.cpp runtime and vLLM guide, introduces a new q8_0 GGUF export feature, and fixes a bug related to duplicate result keys in GLM ASR.

Key Highlights

Added q8_0 GGUF export capability with half-size encoders
Enhanced documentation for llama.cpp and vLLM guides
Fixed duplicate result keys for duplicate audio basenames in GLM ASR
Updated README with holistic fixes and namespace changes

New Features

q8_0 GGUF export feature

Full Release Notes

## What's Changed
* docs(vllm_guide): explain EmbedsPrompt/streaming partial/SPK/concurre… by @qiulang in https://github.com/modelscope/FunASR/pull/3011
* docs(README): make the llama.cpp/GGUF (CPU/edge) runtime a first-class section by @LauraGPT in https://github.com/modelscope/FunASR/pull/3012
* feat: q8_0 GGUF export — half-size encoders, CER unchanged by @LauraGPT in https://github.com/modelscope/FunASR/pull/3013
* docs(README): refresh What's New with June updates by @LauraGPT in https://github.com/modelscope/FunASR/pull/3015
* docs(README): holistic fixes — broken quickstart, stray links, consistency by @LauraGPT in https://github.com/modelscope/FunASR/pull/3016
* docs(README): canonical iic/ ModelScope namespace by @LauraGPT in https://github.com/modelscope/FunASR/pull/3017
* fix(glm_asr): dedup result keys for duplicate audio basenames by @SuperMarioYL in https://github.com/modelscope/FunASR/pull/3014


**Full Changelog**: https://github.com/modelscope/FunASR/compare/v1.3.12...v1.3.13