v2.12.0
xorbitsai/inferencev2.12.0Jul 4, 2026by XprobeBot
AI Summary
This release introduces security controls for remote code execution, new user and API key management UI, and expanded support for models like VibeThinker and Nex-N2. It also enhances monitoring capabilities by splitting Grafana dashboards and unifying worker labels.
Key Highlights
- Gate model remote-code execution behind a config switch
- New UI: API key management and user management pages
- New models: VibeThinker 1.5B/3B, Nex-N2 series, and Ornith-1.0-35B
- Monitoring: Split Grafana dashboard into 6 sub-dashboards
- Log rotation: Daily+size mode with multi-process safety
New Features
- Gate model remote-code execution
- UI: API key management and user management pages
- UI: Ability panel (Embed, Rerank)
- UI: Worker IP multi-select selector
- Models: VibeThinker, Nex-N2, Ornith-1.0-35B, Unlimited-OCR
- Monitoring: Unified worker labels with replica_index
- Log: Daily+size rotation mode
- Core: Model autostart config
- LLM: Permission/scope alignment
Full Release Notes
# What's new in 2.12.0 (2026-07-04) These are the changes in inference v2.12.0. ## New features * feat: gate model remote-code execution behind a config switch by @qxyuan853 in https://github.com/xorbitsai/inference/pull/5027 * FEAT: [UI] add API key management and user management pages by @yiboyasss in https://github.com/xorbitsai/inference/pull/5065 * FEAT: [UI] ability panel add(Embed、Rerank) by @maoyuehui in https://github.com/xorbitsai/inference/pull/5078 * feat(monitor): split Grafana dashboard into 6 sub-dashboards with config store by @m199369309 in https://github.com/xorbitsai/inference/pull/5073 * feat(metrics): unify worker labels with supervisor and add replica_index by @m199369309 in https://github.com/xorbitsai/inference/pull/5075 * feat: register VibeThinker 1.5B / 3B (transformers + vLLM) by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5085 * feat: register Nex-N2 series (mini / Pro / Pro-fp8) by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5094 * feat(log): add daily+size rotation mode with multi-process safety by @m199369309 in https://github.com/xorbitsai/inference/pull/5083 * feat(models): add model autostart config by @bluefish-08 in https://github.com/xorbitsai/inference/pull/5076 * FEAT(webui): replace worker IP input with a filtered multi-select selector by @leslie2046 in https://github.com/xorbitsai/inference/pull/5099 * feat: add Unlimited-OCR support by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5103 * Feat: (UI) running model add Try to API and add useMenuAuth hook by @maoyuehui in https://github.com/xorbitsai/inference/pull/5098 * feat(llm): register Ornith-1.0-35B by @m199369309 in https://github.com/xorbitsai/inference/pull/5119 * feat: permission/scope alignment (core — no live-read) by @m199369309 in https://github.com/xorbitsai/inference/pull/5133 ## Enhancements * ENH: update models JSON [embedding] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5067 * ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5093 * ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5096 * ENH: update model "qwen3.5" JSON by @llyycchhee in https://github.com/xorbitsai/inference/pull/5100 * ENH: update models JSON [image] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5109 * ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5123 * ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5124 ## Bug fixes * fix: avoid blocking the event loop in async update_model_type by @kratos0718 in https://github.com/xorbitsai/inference/pull/5055 * BUG: Fix llama.cpp backend by @codingl2k1 in https://github.com/xorbitsai/inference/pull/5056 * FIX: [model] chat template analysis error by @llyycchhee in https://github.com/xorbitsai/inference/pull/5060 * fix(embedding): pin peft/transformers for jina-embeddings-v5 series by @m199369309 in https://github.com/xorbitsai/inference/pull/5061 * fix(docker): cap fastapi<0.137 in image requirements to match setup.cfg (#5063) by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5072 * fix(device_utils): tolerate unsupported nvmlDeviceGetUtilizationRates in WSL2 by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5070 * fix(audio): resolve Qwen3-ASR forced aligner via ModelScope when it is the active source by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5077 * fix(core): prevent worker metrics loss when cache_tracker init fails by @m199369309 in https://github.com/xorbitsai/inference/pull/5071 * fix(monitor): add model_name label to api_key_requests_total counter by @m199369309 in https://github.com/xorbitsai/inference/pull/5074 * fix: drop stale running models without replica info in supervisor.list_models by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5087 * fix(core): harden sub-pool creation and clean GPU orphans on startup by @m199369309 in https://github.com/xorbitsai/inference/pull/5095 * fix: handle DynamicCache in get_batch_size_and_seq_len_from_kv_cache when HybridCache is importable by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5086 * fix(oauth2): verify JWT expiration in AuthService (#5058) by @qfmy83 in https://github.com/xorbitsai/inference/pull/5088 * fix(oauth2): block privilege escalation in user permission grants (#5058) by @qfmy83 in https://github.com/xorbitsai/inference/pull/5089 * fix(llm/cache): clear error and ensure cache parent dir on file:// model_uri (#5091) by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5097 * fix(vllm): silence repeated GuidedDecodingParams info log per request by @m199369309 in https://github.com/xorbitsai/inference/pull/5120 * fix(llm): install ninja in qwen3.5/qwen3.6 vLLM venv for FlashInfer JIT by @m199369309 in https://github.com/xorbitsai/inference/pull/5118 * fix(llm): normalize tool_call arguments to dict for Qwen3 family templates by @m199369309 in https://github.com/xorbitsai/inference/pull/5129 ## Documentation * doc: add v2.11.0 release notes by @qinxuye in https://github.com/xorbitsai/inference/pull/5057 * doc: add security policy by @qinxuye in https://github.com/xorbitsai/inference/pull/5092 * doc: add Spanish (es) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5112 * doc: add French (fr) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5113 * doc: add i18n translations for Japanese by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5082 * doc: add German (de) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5105 * doc: add Italian (it) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5114 * doc: add Korean (ko) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5115 * doc: add Portuguese (Brazil) (pt-br) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5116 * doc: add Traditional Chinese (zh-tw) documentation translations by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5117 * doc: expand scan_po_issues.py for all translated locales by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5128 ## Others * ci: prepare GPU T4 runner migration by @qinrui777 in https://github.com/xorbitsai/inference/pull/5081 * docs: add and update multi-language README files by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5068 * chore: rename XProbe Inc. to Xinference Holdings Pte. Ltd and unify copyright year to 2026 by @yiboyasss in https://github.com/xorbitsai/inference/pull/5110 * chore: update copyright and restrict Ascend NPU docs to zh-CN by @kejhz653-stack in https://github.com/xorbitsai/inference/pull/5126 ## New Contributors * @kratos0718 made their first contribution in https://github.com/xorbitsai/inference/pull/5055 * @qxyuan853 made their first contribution in https://github.com/xorbitsai/inference/pull/5027 * @kejhz653-stack made their first contribution in https://github.com/xorbitsai/inference/pull/5068 * @qfmy83 made their first contribution in https://github.com/xorbitsai/inference/pull/5088 **Full Changelog**: https://github.com/xorbitsai/inference/compare/v2.11.0...v2.12.0