Hitonabi/mission-control-v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Brain-Bench + Latenz-Metrik (Review P1-9/P1-10)

Browse Source 
- Bench-Matrix Qwen3.6 (5 Configs, separater Port): MTP n-max 3 bestaetigt (+26% tg),
  n-max 4 lohnt nicht, KV Q8_0 gratis (78,6=78,6 t/s) bei halbem KV-Speicher
- deploy-Config: -ctk/-ctv q8_0 am hermes-Eintrag (Live-Schaltung: User-Freigabe noetig)
- voice.py: chat_first_content-Metrik (echte Hirn-Latenz bis erster Inhalts-Token)
- Report um Umsetzungs-Nachtrag ergaenzt

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-07-02 10:56:23 +02:00
parent 45fb61000a
commit e08d812598
3 changed files with 34 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deploy/llama-swap.config.yaml
+1 -1
View File
@@ -5,7 +5,7 @@ globalTTL: 0
models:
Qwen3.6-35B-A3B:
cmd: |
llama-server -m /srv/models/Qwen3.6-35B-A3B-MTP-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 65536 -ngl 999 -fa on --no-mmap --jinja --parallel 1 -cram 16384 --spec-type draft-mtp --spec-draft-n-max 3
llama-server -m /srv/models/Qwen3.6-35B-A3B-MTP-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 65536 -ngl 999 -fa on --no-mmap --jinja --parallel 1 -cram 16384 -ctk q8_0 -ctv q8_0 --spec-type draft-mtp --spec-draft-n-max 3
ttl: 0
aliases:
- hermes