Added llama.cpp on ai
Auto-update README / Generate README and Create MR (push) Failing after 10m17s
Check with kubeconform / lint (push) Failing after 11m23s
Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 12m29s

This commit is contained in:
Ultradesu
2026-06-04 16:59:58 +03:00
parent 6b717f5219
commit 82dbe84075
5 changed files with 125 additions and 0 deletions
+12
View File
@@ -0,0 +1,12 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: llamacpp-config
data:
LLAMA_CACHE: /models
LLAMA_ARG_HOST: 0.0.0.0
LLAMA_ARG_PORT: "8080"
LLAMA_ARG_HF_REPO: unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q6_K
LLAMA_ARG_CTX_SIZE: "32768"
LLAMA_ARG_FLASH_ATTN: auto
LLAMA_ARG_FIT: "on"