owen/inference-worker
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

prepare for production release

Browse Source
This commit is contained in:
mags0ft
2025-11-19 18:40:00 +01:00
parent c42b80ebbd
commit 381ed9ffff
2 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.runpod/hub.json
+1 -1
View File
@@ -14,7 +14,7 @@
{ {
"key": "LLAMA_SERVER_CMD_ARGS", "key": "LLAMA_SERVER_CMD_ARGS",
"input": { "input": {
"name": "Model Name", "name": "Command line arguments for llama-server",
"type": "string", "type": "string",
"description": "Launch command line arguments (argv) for the llama-server binary. Do not define the port.", "description": "Launch command line arguments (argv) for the llama-server binary. Do not define the port.",
"default": "-hf unsloth/gemma-3-270m-it-GGUF:Q6_K --ctx-size 4096", "default": "-hf unsloth/gemma-3-270m-it-GGUF:Q6_K --ctx-size 4096",
src/engine.py
-1
View File
@@ -21,7 +21,6 @@ Typical usage:
""" """
import json import json
import os
from dotenv import load_dotenv from dotenv import load_dotenv
from openai import OpenAI from openai import OpenAI