Files
colibri/c
bokiko 37da111bb4 glm: pin draft+verify to one kernel family during speculation; soften MTP guard (#163)
MTP acceptance collapses when the draft (S=1) and verify (S>=2) forwards do
not compute the same function. Three switches were S-dependent: the int4
IDOT gate (S>=g_i4s, asymmetric exactly on ISAs where g_i4s>1), the
S==1-only fused gate+up pair, and the Metal GEMM row threshold.

SPEC_PIN=1 (default) pins every forward issued while model drafts are live
to the platform S=1 kernel family, so draft and verify agree by
construction. Prefill and non-speculative decode keep their gates.
SPEC_PIN=0 restores the old behavior for A/B.

The 24-proposal <10% guard now pauses drafting for 256 tokens and re-arms
on a fresh window instead of latching off for the whole session.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-16 01:36:15 +03:00
..
2026-07-15 12:42:13 +02:00