Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion third_party/inference
Submodule inference updated 65 files
+56 −0 .github/actions/check-release-permission/action.yaml
+13 −1 .github/workflows/docker-cd.yaml
+42 −66 .github/workflows/pr_auto_run_gen_docs.yaml
+14 −1 .github/workflows/release.yaml
+3 −3 README.md
+3 −3 README_zh_CN.md
+2 −0 doc/source/getting_started/release_notes.rst
+37 −29 doc/source/locale/zh_CN/LC_MESSAGES/getting_started/release_notes.po
+92 −0 monitor/alert/README.md
+92 −0 monitor/alert/README_zh-CN.md
+65 −0 monitor/alert/rules-ja.yml
+65 −0 monitor/alert/rules-ko.yml
+65 −0 monitor/alert/rules-zh-CN.yml
+65 −0 monitor/alert/rules.yml
+75 −0 monitor/dashboard/README.md
+75 −0 monitor/dashboard/README_zh-CN.md
+48 −0 monitor/dashboard/dcgm-custom-metrics.csv
+48 −0 monitor/dashboard/dcgm-custom-metrics.zh-CN.csv
+33 −0 monitor/dashboard/dcgm-exporter.yml
+6,021 −0 monitor/dashboard/xinference-grafana-dashboard-en.json
+6,021 −0 monitor/dashboard/xinference-grafana-dashboard-ja.json
+6,021 −0 monitor/dashboard/xinference-grafana-dashboard-ko.json
+6,021 −0 monitor/dashboard/xinference-grafana-dashboard-zh-CN.json
+1 −1 setup.cfg
+56 −9 xinference/api/restful_api.py
+14 −0 xinference/api/routers/admin.py
+8 −1 xinference/constants.py
+420 −11 xinference/core/metrics.py
+122 −14 xinference/core/model.py
+174 −7 xinference/core/supervisor.py
+1 −1 xinference/core/tests/test_metrics.py
+252 −21 xinference/core/worker.py
+1 −1 xinference/deploy/cmdline.py
+1 −1 xinference/deploy/docker/Dockerfile.aarch64
+8 −2 xinference/model/embedding/__init__.py
+1 −0 xinference/model/embedding/core.py
+6 −3 xinference/model/embedding/model_spec.json
+71 −46 xinference/model/embedding/sentence_transformers/core.py
+119 −95 xinference/model/embedding/sentence_transformers/tests/test_jina_task_mapping.py
+5 −2 xinference/model/embedding/vllm/core.py
+22 −0 xinference/model/llm/__init__.py
+4 −3 xinference/model/llm/llm_family.json
+1 −1 xinference/model/llm/mlx/core.py
+37 −4 xinference/model/llm/reasoning_parser.py
+20 −30 xinference/model/llm/tests/test_utils.py
+22 −9 xinference/model/llm/tool_parsers/qwen_tool_parser.py
+1 −0 xinference/model/llm/transformers/multimodal/qwen2_vl.py
+6 −310 xinference/model/llm/utils.py
+5 −3 xinference/model/llm/vllm/core.py
+56 −0 xinference/model/llm/vllm/patches/__init__.py
+25 −0 xinference/model/llm/vllm/patches/_base.py
+198 −0 xinference/model/llm/vllm/patches/hybrid_kv_cache_page_size.py
+8 −2 xinference/model/rerank/__init__.py
+2 −0 xinference/model/rerank/core.py
+23 −17 xinference/model/rerank/sentence_transformers/core.py
+8 −0 xinference/ui/web/ui/src/components/MenuSide.js
+8 −1 xinference/ui/web/ui/src/components/fetcher.js
+55 −0 xinference/ui/web/ui/src/components/grafanaUtils.js
+2 −6 xinference/ui/web/ui/src/components/utils.js
+22 −0 xinference/ui/web/ui/src/locales/en.json
+22 −0 xinference/ui/web/ui/src/locales/ja.json
+22 −0 xinference/ui/web/ui/src/locales/ko.json
+22 −0 xinference/ui/web/ui/src/locales/zh.json
+5 −0 xinference/ui/web/ui/src/router/index.js
+53 −0 xinference/ui/web/ui/src/scenes/monitoring/index.js
Loading