inference Releases
114 releases of xorbitsai/inference
- v3.19.33.19.3
Sep 7, 2025
- v1.9.1
This release adds support for Qwen-Image model with image editing capabilities, Wan 2.2 model, and various audio and embedding enhancements.
Aug 30, 2025
- v1.9.0
This release introduces Qwen-Image model support, GLM 4.5 series support, and enhanced rerank model engine switching capabilities.
Aug 16, 2025
- v1.8.1
This release adds comprehensive Qwen3 series support, GLM-4.5 series support, and various UI enhancements including virtualenv support and user favorites.
Aug 3, 2025
- v1.8.0
This release introduces llama.cpp backend support for embeddings, non-stream tool calling for sglang, and migration support for custom models.
Jul 20, 2025
- v1.7.1.post1
This is a post-release patch for v1.7.1 that fixes transformers version pinning to resolve SentenceTransformer import errors.
Jun 30, 2025
- v1.7.1
This release adds various UI enhancements, async client support, MLU device support, and vLLM v1 auto enabling, along with several bug fixes.
Jun 27, 2025
- v1.7.0.post1
A patch release focusing on bug fixes for Qwen3-rerank and MiniCPM4 model initialization issues.
Jun 13, 2025
- v1.7.0
A major feature release adding support for CogView4, MiniCPM4, Qwen3, and DeepSeek-R1 models, along with UI enhancements including Japanese and Korean language support.
Jun 13, 2025
- v1.6.1
Feature release focusing on llama.cpp backend improvements, adding multimodal support and new Deepseek models.
May 30, 2025
- v1.6.0.post1
A minor build configuration fix release to resolve setup.cfg issues.
May 17, 2025
- v1.6.0
A major release introducing new models (XiYanSQL, HuatuoGPT-o1, DianJin-R1), image-to-video generation, and extensive quantization support (AWQ, GPTQ).
May 16, 2025
- v1.5.1
Feature release adding Wan 2.1 text-to-video, Qwen3 support, and GGUF v2 support for vLLM.
Apr 30, 2025
- v1.5.0.post2
Minor release including Docker build enhancements and UI bug fixes.
Apr 21, 2025
- v1.5.0.post1
A build configuration fix release to resolve CPU Docker build issues.
Apr 19, 2025
- v1.5.0
Major release introducing InternVL3 and Megatts3 models, AWQ quantization, and UI improvements for progress tracking.
Apr 19, 2025
- v0.0.1
Minimal release notes: "**Full Changelog**: https://github.com/agentheroes/agentheroes/commits/v0.0.1"
Apr 8, 2025
- v1.4.1
Feature release focusing on distributed inference, DeepSeek-VL2 support, and internal quantization library updates.
Apr 3, 2025
- v1.4.0
This release introduces support for Gemma-3 text and vision models, along with DeepSeek V3 function calling. It includes various UI enhancements, bug fixes for different backends (vLLM, xllamacpp, MLX), and documentation updates.
Mar 21, 2025
- v1.3.1.post1
A minor post-release patch addressing specific bugs related to the QwQ-32B model, including a reasoning content parser fix and a download retry issue.
Mar 11, 2025