v0.11.2
版本发布时间: 2024-05-24 17:10:43
xorbitsai/inference最新发布版本:v0.11.3(2024-05-31 17:28:11)
What's new in 0.11.2 (2024-05-24)
These are the changes in inference v0.11.2.
New features
- FEAT: Add command cal-model-mem by @frostyplanet in https://github.com/xorbitsai/inference/pull/1460
- FEAT: add deepseek llm and coder base by @qinxuye in https://github.com/xorbitsai/inference/pull/1533
- FEAT: add codeqwen1.5 by @qinxuye in https://github.com/xorbitsai/inference/pull/1535
- FEAT: Auto detect rerank type for unknown rerank type by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1538
- FEAT: Provide the functionality to query information on various cached models hosted on the query node. by @hainaweiben in https://github.com/xorbitsai/inference/pull/1522
Enhancements
- ENH: Compatible with
huggingface-hub
v0.23.0
by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/1514 - ENH: convert command-r to chat by @qinxuye in https://github.com/xorbitsai/inference/pull/1537
- ENH: Support Intern-VL-Chat model by @amumu96 in https://github.com/xorbitsai/inference/pull/1536
- BLD: adapt to langchain 0.2.x, which has breaking changes by @mikeshi80 in https://github.com/xorbitsai/inference/pull/1521
- BLD: Fix pre commit by @frostyplanet in https://github.com/xorbitsai/inference/pull/1527
- BLD: compatible with torch 2.3.0 by @qinxuye in https://github.com/xorbitsai/inference/pull/1534
Bug fixes
- BUG: Fix start worker failed due to None device name by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1539
- BUG: Fix gpu_idx allocate error when set replica > 1 by @amumu96 in https://github.com/xorbitsai/inference/pull/1528
Others
- CHORE: Basic benchmark/benchmark_rerank.py by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1479
Full Changelog: https://github.com/xorbitsai/inference/compare/v0.11.1...v0.11.2