Skip to content

llama should have None max length #348

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
sam-scale merged 1 commit into from
Oct 24, 2023
Merged

llama should have None max length #348

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
6 changes: 3 additions & 3 deletions model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,14 +152,14 @@
# We need a dict where if we need to override we can
# NOTE: These are in *descending* order of priority. e.g. if you see 'mammoth-coder'
# you'll use that override and not listen to the 'llama-2' override
_VLLM_MODEL_LENGTH_OVERRIDES: Dict[str, Dict[str, int]] = {
_VLLM_MODEL_LENGTH_OVERRIDES: Dict[str, Dict[str, Optional[int]]] = {
"mammoth-coder": {"max_model_len": 16384, "max_num_batched_tokens": 16384},
# Based on config here: https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-7B/blob/main/config.json#L12
# Can also see 13B, 34B there too
"code-llama": {"max_model_len": 16384, "max_num_batched_tokens": 16384},
# Based on config here: https://huggingface.co/codellama/CodeLlama-7b-hf/blob/main/config.json#L12
# Can also see 13B, 34B there too
"llama-2": {"max_model_len": 4096, "max_num_batched_tokens": 4096},
"llama-2": {"max_model_len": None, "max_num_batched_tokens": 4096},
Copy link
Copy Markdown
Contributor

@yunfeng-scale yunfeng-scale Oct 24, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

with vllm-project/vllm#1198 i think we can remove setting max_num_batched_tokens. this is merged in 0.2.0

"mistral": {"max_model_len": 8000, "max_num_batched_tokens": 8000},
}

Expand Down Expand Up @@ -534,7 +534,7 @@ async def create_vllm_bundle(
):
command = []

max_num_batched_tokens: int = 2560 # vLLM's default
max_num_batched_tokens: Optional[int] = 2560 # vLLM's default
max_model_len: Optional[int] = None

for key, value in _VLLM_MODEL_LENGTH_OVERRIDES.items():
Expand Down