From 2b4e58a92601fb4d68c9b7055fb9f24ee8577169 Mon Sep 17 00:00:00 2001 From: Frank Date: Thu, 13 Aug 2026 23:02:07 -0700 Subject: [PATCH] dankclaw: MTP tuning - spec-draft-n-max 2 Retest MTP at n_max 2 (vs 3) for the acceptance/speed tradeoff, keeping MTP-alone + ubatch 8192. Re-benches gen t/s and re-runs the strict parallel-safety test. --- 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 97adfce..036a517 100644 --- a/scripts/frank-default-large.env +++ b/scripts/frank-default-large.env @@ -19,7 +19,7 @@ SPEC_TYPE=draft-mtp # 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 # Draft length per spec type: dflash 8, mtp 2-3. -SPEC_DRAFT_N_MAX=3 +SPEC_DRAFT_N_MAX=2 SPEC_NGRAM_MOD_N_MIN=48 SPEC_NGRAM_MOD_N_MAX=64 SPEC_NGRAM_MOD_N_MATCH=24