Skip to content

dynamic model switch #2211

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

dynamic model switch #2211

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dcf6bb3
dynamic model switch
Aug 20, 2025
0e24728
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Aug 20, 2025
e13beb8
Merge branch 'main' into dynamic_model
srinarayan-srikanthan Sep 26, 2025
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
4 changes: 2 additions & 2 deletions ChatQnA/chatqna.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ def align_inputs(self, inputs, cur_node, runtime_graph, llm_parameters_dict, **k
elif self.services[cur_node].service_type == ServiceType.LLM:
# convert TGI/vLLM to unified OpenAI /v1/chat/completions format
next_inputs = {}
next_inputs["model"] = LLM_MODEL
next_inputs["model"] = inputs["model"]
next_inputs["messages"] = [{"role": "user", "content": inputs["inputs"]}]
next_inputs["max_tokens"] = llm_parameters_dict["max_tokens"]
next_inputs["top_p"] = llm_parameters_dict["top_p"]
Expand Down Expand Up @@ -396,7 +396,7 @@ async def handle_request(self, request: Request):
repetition_penalty=chat_request.repetition_penalty if chat_request.repetition_penalty else 1.03,
stream=stream_opt,
chat_template=chat_request.chat_template if chat_request.chat_template else None,
model=chat_request.model if chat_request.model else None,
model=chat_request.model if chat_request.model else LLM_MODEL,
)
retriever_parameters = RetrieverParms(
search_type=chat_request.search_type if chat_request.search_type else "similarity",
Expand Down
3 changes: 2 additions & 1 deletion CodeGen/codegen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ def align_inputs(self, inputs, cur_node, runtime_graph, llm_parameters_dict, **k
elif self.services[cur_node].service_type == ServiceType.LLM:
# convert TGI/vLLM to unified OpenAI /v1/chat/completions format
next_inputs = {}
next_inputs["model"] = LLM_MODEL_ID
next_inputs["model"] = inputs["model"]
next_inputs["messages"] = [{"role": "user", "content": inputs["query"]}]
next_inputs["max_tokens"] = llm_parameters_dict["max_tokens"]
next_inputs["top_p"] = llm_parameters_dict["top_p"]
Expand Down Expand Up @@ -195,6 +195,7 @@ async def handle_request(self, request: Request):
repetition_penalty=chat_request.repetition_penalty if chat_request.repetition_penalty else 1.03,
stream=stream_opt,
index_name=chat_request.index_name,
model=chat_request.model if chat_request.model else LLM_MODEL_ID,
)

# Initialize the initial inputs with the generated prompt
Expand Down
Loading