What's new in 2.11.0 (2026-06-19)

These are the changes in inference v2.11.0.

New features

• feat: new UI part 3 by @maoyuehui in https://github.com/xorbitsai/inference/pull/5011
• feat: add MiniCPM5-1B model support by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5010
• feat(ui): add change password for local users in user management by @m199369309 in https://github.com/xorbitsai/inference/pull/5014
• feat: add jina-embeddings-v5 series support by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5018
• feat: add Gradio test page for embedding models by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5022
• feat: add MiniCPM-V-4.6 series support by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5025
• feat: add Tencent Hy-MT2 series support by @xiaoyesoso in https://github.com/xorbitsai/inference/pull/5029
• feat(vllm): support glm5 tool parser by @llyycchhee in https://github.com/xorbitsai/inference/pull/5019
• feat(core): add model loading state machine to prevent routing to loading models by @m199369309 in https://github.com/xorbitsai/inference/pull/5032
• feat(audio): add VoxCPM2 model support by @bluefish-08 in https://github.com/xorbitsai/inference/pull/5045
• feat: new UI part 4 by @maoyuehui in https://github.com/xorbitsai/inference/pull/5040
• FEAT: [model] PaddleOCR-VL-1.6 support by @llyycchhee in https://github.com/xorbitsai/inference/pull/5033
• feat: add random serving benchmark workload by @qinxuye in https://github.com/xorbitsai/inference/pull/5036
• feat: new UI part 5 by @maoyuehui in https://github.com/xorbitsai/inference/pull/5053

Enhancements

• ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5017
• ENH: update models JSON [embedding] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5020
• ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5026
• ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5034
• ENH: update models JSON [llm] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5038
• ENH: update models JSON [audio] by @XprobeBot in https://github.com/xorbitsai/inference/pull/5050
• bld: Replace self-hosted runner with GitHub hosted runner and update actions by @qinrui777 in https://github.com/xorbitsai/inference/pull/5000

Bug fixes

• fix(supervisor): self-heal worker registry after supervisor restart by @m199369309 in https://github.com/xorbitsai/inference/pull/4998
• fix(metrics): drop stale series and add unexpected termination gauge by @m199369309 in https://github.com/xorbitsai/inference/pull/4999
• fix(worker): ensure subpool monitor starts after append_sub_pool by @m199369309 in https://github.com/xorbitsai/inference/pull/5004
• fix(model_registration):add flexible type by @llyycchhee in https://github.com/xorbitsai/inference/pull/5007
• fix(model): use os._exit for OOM to trigger pool recovery by @m199369309 in https://github.com/xorbitsai/inference/pull/5005
• fix(venv): add sentence_transformers dependence by @llyycchhee in https://github.com/xorbitsai/inference/pull/5009
• fix(supervisor): evict dead replica from round-robin when auto-recover exhausted by @m199369309 in https://github.com/xorbitsai/inference/pull/5006
• fix(worker): pop launch_ts in recover_model to avoid strict-constructor crashes by @m199369309 in https://github.com/xorbitsai/inference/pull/5012
• fix(deploy): fix dockerfile.cpu kernels version by @llyycchhee in https://github.com/xorbitsai/inference/pull/5013
• fix(logs): fix empty node filter dropdown and redesign toolbar layout by @m199369309 in https://github.com/xorbitsai/inference/pull/5015
• fix(monitor): correct alert rule labels/expressions and add 4 new rules by @m199369309 in https://github.com/xorbitsai/inference/pull/5016
• fix: pin FastAPI below 0.137 for metrics middleware by @qinxuye in https://github.com/xorbitsai/inference/pull/5042
• fix(core): sync model_serve_count gauge on stream request completion by @m199369309 in https://github.com/xorbitsai/inference/pull/5041
• fix(vllm): force spawn for single-GPU EngineCore and fix health check scheduling by @m199369309 in https://github.com/xorbitsai/inference/pull/5030
• fix(worker): strip test envs before recover and clean up GPU orphans by @m199369309 in https://github.com/xorbitsai/inference/pull/5031
• fix(rerank/llama.cpp): honor flat launch kwargs (n_ctx/n_batch/n_ubatch) so rerankers aren't capped at default ubatch (#5001) by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5046
• fix(anthropic): honor top-level system prompt and inline system messages (#5037) by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5049
• fix(vllm/patches): auto-apply hybrid KV cache patch to Qwen3-Next by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5052
• fix(audio): warn and ignore non-zero temperature for Qwen3-ASR instead of raising by @Anai-Guo in https://github.com/xorbitsai/inference/pull/5054

Documentation

• doc: add v2.10.0 release notes by @qinxuye in https://github.com/xorbitsai/inference/pull/4997
• doc: hide Zhihu link from English docs by @qinxuye in https://github.com/xorbitsai/inference/pull/5008
• doc: update documentation logo and favicon by @qinxuye in https://github.com/xorbitsai/inference/pull/5024
• doc: update Read the Docs build image by @qinxuye in https://github.com/xorbitsai/inference/pull/5044

Others

• docs: add Telegram community links by @qinxuye in https://github.com/xorbitsai/inference/pull/5003

New Contributors

• @qinrui777 made their first contribution in https://github.com/xorbitsai/inference/pull/5000
• @xiaoyesoso made their first contribution in https://github.com/xorbitsai/inference/pull/5010
• @bluefish-08 made their first contribution in https://github.com/xorbitsai/inference/pull/5045
• @Anai-Guo made their first contribution in https://github.com/xorbitsai/inference/pull/5046

Full Changelog: https://github.com/xorbitsai/inference/compare/v2.10.0...v2.11.0