Commit 318ade3
- .github/actions/check-release-permission/action.yaml+56
- .github/workflows/docker-cd.yaml+13-1
- .github/workflows/pr_auto_run_gen_docs.yaml+42-66
- .github/workflows/release.yaml+14-1
- README.md+3-3
- README_zh_CN.md+3-3
- doc/source/getting_started/release_notes.rst+2
- doc/source/locale/zh_CN/LC_MESSAGES/getting_started/release_notes.po+37-29
- monitor/alert/README.md+92
- monitor/alert/README_zh-CN.md+92
- monitor/alert/rules-ja.yml+65
- monitor/alert/rules-ko.yml+65
- monitor/alert/rules-zh-CN.yml+65
- monitor/alert/rules.yml+65
- monitor/dashboard/README.md+75
- monitor/dashboard/README_zh-CN.md+75
- monitor/dashboard/dcgm-custom-metrics.csv+48
- monitor/dashboard/dcgm-custom-metrics.zh-CN.csv+48
- monitor/dashboard/dcgm-exporter.yml+33
- monitor/dashboard/xinference-grafana-dashboard-en.json+6.0k
- monitor/dashboard/xinference-grafana-dashboard-ja.json+6.0k
- monitor/dashboard/xinference-grafana-dashboard-ko.json+6.0k
- monitor/dashboard/xinference-grafana-dashboard-zh-CN.json+6.0k
- setup.cfg+1-1
- xinference/api/restful_api.py+56-9
- xinference/api/routers/admin.py+14
- xinference/constants.py+8-1
- xinference/core/metrics.py+420-11
- xinference/core/model.py+122-14
- xinference/core/supervisor.py+174-7
- xinference/core/tests/test_metrics.py+1-1
- xinference/core/worker.py+252-21
- xinference/deploy/cmdline.py+1-1
- xinference/deploy/docker/Dockerfile.aarch64+1-1
- xinference/model/embedding/__init__.py+8-2
- xinference/model/embedding/core.py+1
- xinference/model/embedding/model_spec.json+6-3
- xinference/model/embedding/sentence_transformers/core.py+71-46
- xinference/model/embedding/sentence_transformers/tests/test_jina_task_mapping.py+119-95
- xinference/model/embedding/vllm/core.py+5-2
- xinference/model/llm/__init__.py+22
- xinference/model/llm/llm_family.json+4-3
- xinference/model/llm/mlx/core.py+1-1
- xinference/model/llm/reasoning_parser.py+37-4
- xinference/model/llm/tests/test_utils.py+20-30
- xinference/model/llm/tool_parsers/qwen_tool_parser.py+22-9
- xinference/model/llm/transformers/multimodal/qwen2_vl.py+1
- xinference/model/llm/utils.py+6-310
- xinference/model/llm/vllm/core.py+5-3
- xinference/model/llm/vllm/patches/__init__.py+56
- xinference/model/llm/vllm/patches/_base.py+25
- xinference/model/llm/vllm/patches/hybrid_kv_cache_page_size.py+198
- xinference/model/rerank/__init__.py+8-2
- xinference/model/rerank/core.py+2
- xinference/model/rerank/sentence_transformers/core.py+23-17
- xinference/ui/web/ui/src/components/MenuSide.js+8
- xinference/ui/web/ui/src/components/fetcher.js+8-1
- xinference/ui/web/ui/src/components/grafanaUtils.js+55
- xinference/ui/web/ui/src/components/utils.js+2-6
- xinference/ui/web/ui/src/locales/en.json+22
- xinference/ui/web/ui/src/locales/ja.json+22
- xinference/ui/web/ui/src/locales/ko.json+22
- xinference/ui/web/ui/src/locales/zh.json+22
- xinference/ui/web/ui/src/router/index.js+5
- xinference/ui/web/ui/src/scenes/monitoring/index.js+53
0 commit comments