1.1.3 (2026-07-14)
Features
- add NCAI VAETKI model to curated model database (bdbf338)
- add RamaLama as a detection provider (5bef0b2)
Bug Fixes
- hardware: read discrete Intel Arc VRAM from sysfs (xe/i915) (9bbaa8d)
- hardware: read discrete Intel Arc VRAM from sysfs (xe/i915) (9fbbcb8), closes #609
- match Unsloth
-UDdynamic GGUFs to catalog models (b3de39d) - match Unsloth
-UDdynamic GGUFs to catalog models (e9b66be) - name AMD unified APUs when rocm-smi reports "N/A", gate junk shares (ba96f4c)
- name AMD unified APUs when rocm-smi reports "N/A", gate junk shares (e282011)
- providers: detect oMLX as an MLX runtime (f649952)
- providers: show LM Studio/Docker Desktop as installed when idle (bca491e)
- providers: show LM Studio/Docker Desktop as installed when idle (5a22add), closes #731
- serve: include per-GPU memory_bandwidth_gbps in /api/v1/system (ce3f7bf)
- serve: include per-GPU memory_bandwidth_gbps in /api/v1/system (8b9b7aa), closes #747
What's Changed
- fix(providers): detect oMLX as an MLX runtime by @CN-Scars in #701
- feat: add RamaLama as a detection provider by @Olawoyin007 in #700
- fix: match Unsloth
-UDdynamic GGUFs to catalog models by @AlexsJones in #729 - fix(providers): show LM Studio/Docker Desktop as installed when idle by @AlexsJones in #734
- feat: add NCAI VAETKI model to curated model database by @wklee610 in #658
- fix(hardware): read discrete Intel Arc VRAM from sysfs (xe/i915) by @AlexsJones in #733
- chore(deps): bump assert_cmd from 2.2.1 to 2.2.2 by @dependabot[bot] in #579
- chore(deps): bump unicode-segmentation from 1.13.2 to 1.13.3 by @dependabot[bot] in #646
- chore(deps): bump actions/cache from 5.0.5 to 6.1.0 by @dependabot[bot] in #694
- fix: name AMD unified APUs when rocm-smi reports "N/A", gate junk shares by @AlexsJones in #742
- Correct MiniMax M2.7 context window by @octo-patch in #743
- chore(deps): bump docker/metadata-action from 6.0.0 to 6.2.0 by @dependabot[bot] in #741
- chore(deps): bump serde_json from 1.0.149 to 1.0.150 by @dependabot[bot] in #595
- fix(serve): include per-GPU memory_bandwidth_gbps in /api/v1/system by @AlexsJones in #749
- chore(main): release 1.1.3 by @AlexsJones in #727
New Contributors
- @Olawoyin007 made their first contribution in #700
Full Changelog: v1.1.2...v1.1.3