@setoelkahfi / sigit / commits / a0b2ed2

docs(changelog): record Qwen3-14B NaN inference fix (#5)

The Qwen3-14B "Invalid sampling probability ... NaN / NaN/Inf logits" failure is a half-precision (F16) overflow in the onde inference engine on GPUs without bfloat16 support (notably Intel Macs): the 14B model's attention scores exceed F16's range and become NaN. Fixed in onde by preferring F32 over the F16 fallback (see onde/patches/), and siGit now shows an actionable hint instead of the raw engine error. Reaches siGit when the onde dependency is bumped. Refs #5 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0162qAWnHPNWsoD11y3TKPVC

Claude committed Jun 25, 2026 at 15:36 UTC a0b2ed27d7910e04981c10a51fa840d04b54005c
1 file changed +12
CHANGELOG.md
+12
index 9499194..a833abc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,17 @@ # Changelog +## Unreleased + +### Fixed + +* **Qwen3-14B on-device inference** (#5): selecting Qwen3-14B and prompting it failed with + `Inference failed: inference error: Invalid sampling probability at index 0: NaN. The model + likely produced NaN/Inf logits.` This is a half-precision (F16) overflow in the `onde` + inference engine on GPUs without bfloat16 support (notably Intel Macs); the 14B model's + attention scores exceed F16's range and become `NaN`. Fixed in the engine by preferring F32 + over the F16 fallback (see `onde/patches/`), surfaced here once the `onde` dependency is + bumped. siGit also now shows an actionable hint instead of the raw engine error. + ## 1.2.1 Stabilizes the Zed/ACP integration and finishes the cloud-tier wiring on top of 1.2.0.