Skip to content

feat: support custom models vllm serving #2635

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 5, 2023
Merged

feat: support custom models vllm serving #2635

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
da840a7
feat: support custom models vllm serving
congchan Nov 3, 2023
df81b43
fix: reformat for the check
congchan Nov 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 17 additions & 1 deletion fastchat/serve/vllm_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@

from fastapi import FastAPI, Request, BackgroundTasks
from fastapi.responses import StreamingResponse, JSONResponse
import torch
import uvicorn
from vllm import AsyncLLMEngine
from vllm.engine.arg_utils import AsyncEngineArgs
Expand Down Expand Up @@ -231,6 +230,23 @@ async def api_model_details(request: Request):
parser.add_argument(
"--conv-template", type=str, default=None, help="Conversation prompt template."
)
parser.add_argument(
"--trust_remote_code",
action="store_false",
default=True,
help="Trust remote code (e.g., from HuggingFace) when"
"downloading the model and tokenizer.",
)
parser.add_argument(
"--gpu_memory_utilization",
type=float,
default=0.9,
help="The ratio (between 0 and 1) of GPU memory to"
"reserve for the model weights, activations, and KV cache. Higher"
"values will increase the KV cache size and thus improve the model's"
"throughput. However, if the value is too high, it may cause out-of-"
"memory (OOM) errors.",
)

parser = AsyncEngineArgs.add_cli_args(parser)
args = parser.parse_args()
Expand Down