·
352 commits
to croco_exp_0
since this release
Test version post llama_context refactor, following Concedo's merge in KCPP.
Context shift with Gemma 3 (tested with KV 16) seems to be working on my side too.
2 GGML/Cuda "IK" ops are lost, fused_unary and fused_rms_norm, because I'm unable to refactor their LCPP segment. Expect (maybe) a couple of percents of performance loss.
Full Changelog: v1.86004_b4878...v1.86010_4885