0.9.11 (2026-04-19)
Bug Fixes
- MoE GPU-mode TPS uses full model size + expert-count-scaled overhead (#464) (e1f3245)
- read LM Studio download progress from streaming POST response (#467) (3b90e2c), closes #463
- replace unreachable!() with graceful fallback in estimate_tps_with_gpu (#459) (fd1b233)
What's Changed
- fix: replace unreachable!() with graceful fallback in estimate_tps_with_gpu by @RhoMancer in #459
- fix: MoE GPU-mode TPS uses full model size + expert-count-scaled overhead by @RhoMancer in #464
- fix: read LM Studio download progress from streaming POST response by @AlexsJones in #467
- chore(main): release 0.9.11 by @AlexsJones in #466
New Contributors
- @RhoMancer made their first contribution in #459
Full Changelog: v0.9.10...v0.9.11