phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add default for max_seq_len

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-18 21:59:10 -07:00
parent 9ab27e852b
commit f5eda1decf
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/impls/meta_reference/inference/config.py
View file

@ -11,10 +11,10 @@ from llama_models.datatypes import ModelFamily
from llama_models.schema_utils import json_schema_type
from llama_models.sku_list import all_registered_models, resolve_model
from llama_stack.apis.inference import QuantizationConfig
from pydantic import BaseModel, Field, field_validator
from llama_stack.apis.inference import QuantizationConfig
@json_schema_type
class MetaReferenceImplConfig(BaseModel):
@ -24,7 +24,7 @@ class MetaReferenceImplConfig(BaseModel):
)
quantization: Optional[QuantizationConfig] = None
torch_seed: Optional[int] = None
max_seq_len: int
max_seq_len: int = 4096
max_batch_size: int = 1
@field_validator("model")