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

deploy-Config: Kommentar aus dem cmd-Literalblock heraus (waere Teil des Kommandos gewesen)

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-07-02 11:09:29 +02:00
parent 60765469aa
commit a1cea1a1ea
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deploy/llama-swap.config.yaml
+3 -3
View File
@@ -4,10 +4,10 @@ globalTTL: 0
models: models:
Qwen3.6-35B-A3B: Qwen3.6-35B-A3B:
# parallel 2 + c 131072: 2 Slots à 65k (Slot 2 = Mem0-Lern-Extraktion, blockiert Voice-Turns
# nicht mehr); KV Q8_0 macht das speicherneutral zu vorher (65k f16). Bench 2026-07-02:
# Q8_0 kostet 0 t/s, MTP n-max 3 = +26% vs. ohne Spec.
cmd: | cmd: |
# parallel 2 + c 131072: 2 Slots à 65k (Slot 2 = Mem0-Lern-Extraktion, blockiert Voice-Turns
# nicht mehr); KV Q8_0 macht das speicherneutral zu vorher (65k f16). Bench 2026-07-02:
# Q8_0 kostet 0 t/s, MTP n-max 3 = +26% vs. ohne Spec.
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 131072 -ngl 999 -fa on --no-mmap --jinja --parallel 2 -cram 16384 -ctk q8_0 -ctv q8_0 --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 131072 -ngl 999 -fa on --no-mmap --jinja --parallel 2 -cram 16384 -ctk q8_0 -ctv q8_0 --spec-type draft-mtp --spec-draft-n-max 3
ttl: 0 ttl: 0
aliases: aliases: