Skip to content
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

Update vllm to 0.6.2 #3343

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update vllm to 0.6.2 #3343

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion examples/large_models/vllm/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
vllm==0.6.1.post2
vllm==0.6.2
11 changes: 8 additions & 3 deletions ts/torch_handler/vllm_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
)
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.entrypoints.openai.serving_completion import OpenAIServingCompletion
from vllm.entrypoints.openai.serving_engine import LoRAModulePath
from vllm.entrypoints.openai.serving_engine import BaseModelPath, LoRAModulePath

from ts.handler_utils.utils import send_intermediate_predict_response
from ts.service import PredictionException
Expand Down Expand Up @@ -54,6 +54,11 @@ def initialize(self, ctx):
else:
served_model_names = [vllm_engine_config.model]

base_model_paths = [
BaseModelPath(name=name, model_path=vllm_engine_config.model)
for name in served_model_names
]

chat_template = ctx.model_yaml_config.get("handler", {}).get(
"chat_template", None
)
Expand All @@ -64,7 +69,7 @@ def initialize(self, ctx):
self.completion_service = OpenAIServingCompletion(
self.vllm_engine,
model_config,
served_model_names,
base_model_paths,
lora_modules=lora_modules,
prompt_adapters=None,
request_logger=None,
Expand All @@ -73,7 +78,7 @@ def initialize(self, ctx):
self.chat_completion_service = OpenAIServingChat(
self.vllm_engine,
model_config,
served_model_names,
base_model_paths,
"assistant",
lora_modules=lora_modules,
prompt_adapters=None,
Expand Down
Loading