MTP head is int8 by default (int4 head: 0-4% acceptance, unusable — measured in #8); README: honest MTP numbers + M5 Max community datapoint (#4, #5)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-09 20:34:08 +02:00
parent ab6950876b
commit c035f41778
3 changed files with 15 additions and 8 deletions
@@ -409,9 +409,11 @@ def cmd_convert(a):
    rc=subprocess.call(base)
    if rc!=0: sys.exit(rc)
    if a.no_mtp: sys.exit(0)
-    # passo 2: testa MTP (layer 78) -> abilita la decodifica speculativa nativa (piu' veloce)
-    print(f"  {C.dim}[2/2] testa MTP (draft speculativi){C.r}")
-    sys.exit(subprocess.call(base+["--mtp"]))
+    # passo 2: testa MTP (layer 78). SEMPRE int8: a int4 i draft sbagliano quasi sempre
+    # (acceptance 0-4% vs 39-59%, misurato — issue #8) e la speculazione non parte mai.
+    mtp_cmd=list(base); i=mtp_cmd.index("--ebits"); mtp_cmd[i+1]=str(max(8,a.ebits))
+    print(f"  {C.dim}[2/2] testa MTP a int8 (draft speculativi){C.r}")
+    sys.exit(subprocess.call(mtp_cmd+["--mtp"]))

 def main():
    common=argparse.ArgumentParser(add_help=False)