v0.8.3

What's new in 0.8.3 (2024-02-02)

These are the changes in inference v0.8.3.

New features

• FEAT: add whisper.small and belle distilwhisper model, fix parameter in rerank by @zhanghx0905 in #944
• FEAT: Support jina-embeddings-v2-base-zh by @aresnow1 in #948
• FEAT: Support Yi VL by @codingl2k1 in #946
• FEAT: Support more embedding and rerank models by @aresnow1 in #959

Enhancements

• ENH: Record gpu mem status in workers by @ChengjieLi28 in #941
• ENH: Allow chat max_tokens is None by @codingl2k1 in #960
• ENH: chatglm ggml format supports system_prompt by @ChengjieLi28 in #962

Bug fixes

• BUG: Fix roles in chat UI by @aresnow1 in #949
• BUG: Fix heartbeat by @codingl2k1 in #957
• BUG: Fix model's content length by @aresnow1 in #955

Documentation

• DOC: Update readme by @aresnow1 in #938
• DOC: Add image model doc by @codingl2k1 in #947
• DOC: Add audio model doc by @codingl2k1 in #954
• DOC: Reorge model related docs by @onesuper in #961

New Contributors

• @zhanghx0905 made their first contribution in #944

Full Changelog: v0.8.2...v0.8.3

v0.8.2

What's new in 0.8.2 (2024-01-26)

These are the changes in inference v0.8.2.

New features

• FEAT: Support events by @codingl2k1 in #916
• FEAT: Support audio model by @codingl2k1 in #929
• FEAT: Support orion series models by @aresnow1 in #933
• Feat: Support Mixtral-8x7B-Instruct-v0.1-AWQ by @aresnow1 in #936

Enhancements

• ENH: Launch model by version by @ChengjieLi28 in #896
• ENH: Move multimodal to LLM by @codingl2k1 in #917
• ENH: InternLM2 chat template by @aresnow1 in #919
• ENH: Support use_fp16 for rerank model by @aresnow1 in #927
• ENH: record instance count and version count when detailed listing model registrations by @ChengjieLi28 in #920
• BLD: Resolve conflicts during installation by @aresnow1 in #924
• REF: Move auth code to service for better scalability by @ChengjieLi28 in #925

Documentation

• DOC: Update readme by @aresnow1 in #914
• DOC: Display contributors in readme by @onesuper in #915
• DOC: Merge multimodal to LLM by @codingl2k1 in #923
• DOC: Model usage guide by @onesuper in #926
• DOC: Audio doc by @codingl2k1 in #937

Full Changelog: v0.8.1...v0.8.2

v0.8.1

What's new in 0.8.1 (2024-01-19)

These are the changes in inference v0.8.1.

New features

• FEAT: Auto recover limit by @codingl2k1 in #893
• FEAT: Prometheus metrics exporter by @codingl2k1 in #906
• FEAT: Add internlm2-chat support by @aresnow1 in #913

Enhancements

• ENH: Launch model asynchronously by @ChengjieLi28 in #879
• ENH: qwen vl modelscope by @codingl2k1 in #902
• ENH: Add "tools" in model ability by @aresnow1 in #904
• ENH: Add quantization support for qwen chat by @aresnow1 in #910

Bug fixes

• BUG: Fix prompt template of chatglm3-32k by @aresnow1 in #889
• BUG: invalid volumn in docker compose yml by @ChengjieLi28 in #890
• BUG: Revert #883 by @aresnow1 in #903
• BUG: Fix chatglm backend by @codingl2k1 in #898
• BUG: Fix tool calls on custom model by @codingl2k1 in #899
• BUG: Fix is_valid_model_name by @aresnow1 in #907

Documentation

• DOC: Update the documentation about use of docker by @aresnow1 in #901
• DOC:ADD FAQ IN troubleshooting.rst by @sisuad in #911

New Contributors

• @sisuad made their first contribution in #911

Full Changelog: v0.8.0...v0.8.1

v0.8.0

What's new in 0.8.0 (2024-01-11)

These are the changes in inference v0.8.0.

New features

• FEAT: qwen 1.8b gptq by @codingl2k1 in #869
• FEAT: docker compose support by @Minamiyama in #868
• FEAT: Simple OAuth2 system by @ChengjieLi28 in #793
• FEAT: Chat vl web UI by @codingl2k1 in #882
• FEAT: Yi chat gptq by @codingl2k1 in #876

Enhancements

• ENH: Stream use xoscar generator by @codingl2k1 in #859
• ENH: UI supports registering custom gptq models by @ChengjieLi28 in #875
• ENH: make the size param of *_to_image more compatible by @liunux4odoo in #881
• BLD: Update package-lock.json by @aresnow1 in #886
• REF: Add model_hub property in EmbeddingModelSpec by @aresnow1 in #877

Bug fixes

• BUG: Fix image model b64_json output by @codingl2k1 in #874
• BUG: fix libcuda.so.1: cannot open shared object file by @superhuahua in #883
• BUG: Fix auto recover kwargs by @codingl2k1 in #885

Documentation

• DOC: docker image translation by @aresnow1 in #865
• DOC: register model with model_family by @ChengjieLi28 in #863
• DOC: Add OpenAI Client API doc by @codingl2k1 in #864
• DOC: add docker instructions by @onesuper in #878

New Contributors

• @superhuahua made their first contribution in #883

Full Changelog: v0.7.5...v0.8.0

v0.7.5

What's new in 0.7.5 (2024-01-05)

These are the changes in inference v0.7.5.

New features

• FEAT: text2vec by @ChengjieLi28 in #857

Enhancements

• ENH: Offload all response serialization to ModelActor by @codingl2k1 in #837
• ENH: Custom model uses vLLM by @ChengjieLi28 in #861
• BLD: Docker image by @ChengjieLi28 in #855

Bug fixes

• BUG: Fix typing_extension version problem in notebook by @onesuper in #856
• BUG: Fix multimodal cmdline by @codingl2k1 in #850
• BUG: Fix generate of chatglm3 by @aresnow1 in #858

Documentation

• DOC: CUDA Version recommendation by @ChengjieLi28 in #841
• DOC: new doc cover by @onesuper in #843
• DOC: Autogen modelhub info by @onesuper in #845
• DOC: Add multimodal feature in README by @onesuper in #846
• DOC: Chinese doc for user guide by @aresnow1 in #847
• DOC: add notebook for quickstart by @onesuper in #854
• DOC: Add docs about environments by @aresnow1 in #853
• DOC: Add jupyter notebook quick start tutorial by @onesuper in #851

Others

• CHORE: Add docker image with latest tag by @ChengjieLi28 in #862

Full Changelog: v0.7.4.1...v0.7.5

v0.7.4.1

What's new in 0.7.4.1 (2023-12-29)

These are the changes in inference v0.7.4.1.

Documentation

• DOC: Multimodal example by @codingl2k1 in #842

Full Changelog: v0.7.4...v0.7.4.1

v0.7.4

What's new in 0.7.4 (2023-12-29)

These are the changes in inference v0.7.4.

New features

• FEAT: Support sd-turbo by @codingl2k1 in #797
• FEAT: Support Skywork models by @Minamiyama in #809
• FEAT: Support sdxl-turbo by @codingl2k1 in #816
• FEAT: Supports registering rerank models by @ChengjieLi28 in #825
• FEAT: Support Phi-2 by @Bojun-Feng in #828
• FEAT: Support vllm gptq by @codingl2k1 in #832
• FEAT: Support qwen vl chat by @codingl2k1 in #829

Enhancements

• ENH: Custom model can use tool calls by @codingl2k1 in #818
• ENH: Replace uuid with model name for model_uid by @ChengjieLi28 in #831

Bug fixes

• BUG: error when check model_uid & model_name in restful_api by @liunux4odoo in #803
• BUG: launch method exception (#807) by @auxpd in #808
• BUG: Model description does not support Chinese from UI registering by @ChengjieLi28 in #812
• BUG: Find correct class for customized model by @sarsmlee in #835

Documentation

• DOC: add function calling in read me by @onesuper in #804
• DOC: Chinese documents for Logging and Models parts by @ChengjieLi28 in #650
• DOC: remove version limit of sphinx by @qinxuye in #820
• DOC: polish function call description by @onesuper in #821
• DOC: add switcher.json by @qinxuye in #822
• DOC: add document language switcher by @qinxuye in #823
• DOC: use wechat and zhihu for zh doc by @qinxuye in #824
• DOC: Chinese doc for getting started by @aresnow1 in #833
• DOC: simplify entry doc by @onesuper in #826
• DOC: Chinese doc for example part by @ChengjieLi28 in #838

New Contributors

• @liunux4odoo made their first contribution in #803
• @auxpd made their first contribution in #808
• @sarsmlee made their first contribution in #835

Full Changelog: v0.7.3.1...v0.7.4

v0.7.3.1

What's new in 0.7.3.1 (2023-12-22)

These are the changes in inference v0.7.3.1.

Bug fixes

• BUG: Worker starts failed on windows by @ChengjieLi28 in #800

Full Changelog: v0.7.3...v0.7.3.1

v0.7.3

What's new in 0.7.3 (2023-12-22)

These are the changes in inference v0.7.3.

New features

• FEAT: Support OpenHermes 2.5 by @Bojun-Feng in #776
• FEAT: Support deepseek models by @aresnow1 in #786
• FEAT: Support tool message by @codingl2k1 in #794
• FEAT: Support Mixtral-8x7B-v0.1 models by @Bojun-Feng in #782
• FEAT: Support mistral instruct v0.2 by @aresnow1 in #796

Enhancements

• ENH: Enable streaming on Ctransformer by @Bojun-Feng in #784
• ENH: vllm backend support tool calls by @codingl2k1 in #785
• ENH: qwen switch to llama cpp by @codingl2k1 in #778
• ENH: [UI] register custom embedding model by @ChengjieLi28 in #791

Bug fixes

• BUG: UI Crash on Search when model_format and model_size have been selected by @Bojun-Feng in #772
• BUG: When changing XINFERENCE_HOME env, the model files are still stored where they were. by @ChengjieLi28 in #777
• BUG: Remove the modelscope import by @aresnow1 in #788
• BUG: when terminating worker by ctrl+C, supervisor does not remove worker information by @ChengjieLi28 in #779
• BUG: Xinference does not release custom model name when registering failed by @ChengjieLi28 in #790

Documentation

• DOC: Update readme by @aresnow1 in #743
• DOC: Update FunctionCall.ipynb by @codingl2k1 in #773

Full Changelog: v0.7.2...v0.7.3

v0.7.2

What's new in 0.7.2 (2023-12-15)

These are the changes in inference v0.7.2.

New features

• FEAT: Supports qwen-chat 1.8B by @ChengjieLi28 in #757
• FEAT: Support gorilla openfunctions v1 by @codingl2k1 in #760
• FEAT: qwen function call by @codingl2k1 in #763

Enhancements

• ENH: Handle tool call failed by @codingl2k1 in #767

Bug fixes

• BUG: [UI] Fix model size selection crash issue by @ChengjieLi28 in #764

Documentation

• DOC: Fix model_uri missing in Custom Models by @ChengjieLi28 in #759

Full Changelog: v0.7.1...v0.7.2