Add default for max_seq_len

togethercomputer · Sep 19, 2024 · f5eda1d · f5eda1d
1 parent 9ab27e8
commit f5eda1d
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/llama_stack/providers/impls/meta_reference/inference/config.py b/llama_stack/providers/impls/meta_reference/inference/config.py
@@ -11,10 +11,10 @@
 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")