14 days ago
-
Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971
-
Replace all results with the current build (94559012): removed superseded data
-
Hot/cold expert analysis: skew, profile pinning hit rates; fix hit counting and default pin fraction
-
Fix runmem threshold unit bug; re-run all memory tiers enforced (native, v1, v2, v2 forced); add native data and forced-vs-designed explanation
-
Upload v2 memory tiers (default and forced row-parallel) with path counters
-
Add v2 row-parallel for gated Flint experts; label all data v1/v2; fix swiglu_limit pass-through
15 days ago
-
Clarify which EPQ version (v1/v2) is active for Flint
-
Verify EPQ against native llama.cpp; fix swiglu clamp and dump hook; re-run memory tiers
-
Add test system and memory benchmark results to model card
-
Record five Flint RSS watchdog memory tiers
-
Add Flint expert paging port and memory benchmark
