Commit History
-
WARP W1: M=k batched prefill (2.6 -> 11.5 tok/s at M=16, bit-exact) + verifyBatch primitive
humuhumu33 +1: Claude Fable 5Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>0cb508b
-
WARP W0: 27B cross-turn state carry (TTFT no longer grows with history) + incremental detok + specDecode qk_norm lift (byte-identity proven, spec stays opt-in)
humuhumu33 +1: Claude Fable 5Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>1365052 -
Bonsai 27B is now the default: the full 27B mind runs in your browser (4-5 tok/s, watch it think), with a one-tap toggle to the fast 8B. Verified q1 hybrid engine + app bridge.
Humuhumu33730dfb5