From 5dd6949909149cccd6b0b123381e819e88fd20d9 Mon Sep 17 00:00:00 2001 From: Frank Date: Thu, 13 Aug 2026 22:22:29 -0700 Subject: [PATCH] dankclaw: bench cycle 3 - layer ngram-mod under draft-mtp Test the MTP+ngram layering (ngram re-drafts on top of the MTP draft) at ubatch 4096. Must clear the strict parallel-safety test and beat MTP alone (15.3-19.5 t/s) to stay. --- scripts/frank-default-large.env | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env index 07dee93..6935cac 100644 --- a/scripts/frank-default-large.env +++ b/scripts/frank-default-large.env @@ -14,7 +14,7 @@ PARALLEL=3 # draft-mtp - MTP sidecar draft (a4lg/Qwen3.6-27B-MTP-ONLY-Q8_0.gguf) # ngram-mod - draftless ngram matching (no draft model, no shared ctx) # Benched 2026-08-14: see docs/frank-default-large-benchmark.md for the winner. -SPEC_TYPE=draft-mtp +SPEC_TYPE=draft-mtp,ngram-mod # Draft model file (only used when SPEC_TYPE contains 'draft-'). # DFlash: Qwen3.6-27B-DFlash-Q8_0.gguf ; MTP: Qwen3.6-27B-MTP-ONLY-Q8_0.gguf DRAFT_FILE=Qwen3.6-27B-MTP-ONLY-Q8_0.gguf