dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

dankclaw: MTP tuning - spec-draft-n-max 2

Browse Source 
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.
This commit is contained in:
Frank
2026-08-13 23:02:07 -07:00
parent 3c2db64a78
commit 2b4e58a926
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/frank-default-large.env
+1 -1
View File
@@ -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 # 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_FILE=Qwen3.6-27B-MTP-ONLY-Q8_0.gguf
# Draft length per spec type: dflash 8, mtp 2-3. # 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_MIN=48
SPEC_NGRAM_MOD_N_MAX=64 SPEC_NGRAM_MOD_N_MAX=64
SPEC_NGRAM_MOD_N_MATCH=24 SPEC_NGRAM_MOD_N_MATCH=24