bump
This commit is contained in:
+5
-1
@@ -18,7 +18,7 @@ version: "3.8"
|
||||
|
||||
services:
|
||||
llama-server:
|
||||
image: ghcr.io/ggml-org/llama.cpp:server-cuda
|
||||
image: ghcr.io/ggml-org/llama.cpp:server-cuda13
|
||||
container_name: llama-server
|
||||
ports:
|
||||
# Явный IPv4 на хосте (избегаем привязки только к [::] в части окружений).
|
||||
@@ -43,6 +43,10 @@ services:
|
||||
- "0.0.0.0"
|
||||
- "--port"
|
||||
- "8080"
|
||||
- "--spec-type"
|
||||
- "draft-mtp"
|
||||
- "--spec-draft-n-max"
|
||||
- "3"
|
||||
- "--n-cpu-moe"
|
||||
- "${N_CPU_MOE:-99}"
|
||||
- "-c"
|
||||
|
||||
Reference in New Issue
Block a user