minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Fix lora doc (#15282)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-12-16 15:53:38 -08:00
committed by GitHub
parent 930705863f
commit d92c1f8cbd
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/lora.ipynb
+2 -1
View File
@@ -90,11 +90,12 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"server_process, port = launch_server_cmd(\n", "server_process, port = launch_server_cmd(\n",
" # Here we set max-loras-per-batch to 2: one slot for adaptor and another one for base model\n",
" \"\"\"\n", " \"\"\"\n",
"python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n", "python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
" --enable-lora \\\n", " --enable-lora \\\n",
" --lora-paths lora0=algoprog/fact-generation-llama-3.1-8b-instruct-lora \\\n", " --lora-paths lora0=algoprog/fact-generation-llama-3.1-8b-instruct-lora \\\n",
" --max-loras-per-batch 1 \\\n", " --max-loras-per-batch 2 \\\n",
" --log-level warning \\\n", " --log-level warning \\\n",
"\"\"\"\n", "\"\"\"\n",
")\n", ")\n",