mirror of
https://github.com/theroyallab/tabbyAPI.git
synced 2026-03-14 15:57:27 +00:00
Model: Fix gpu split params
GPU split auto is a bool and GPU split is an array of integers for GBs to allocate per GPU. Signed-off-by: kingbri <bdashore3@proton.me>
This commit is contained in:
@@ -15,7 +15,8 @@ class ModelList(BaseModel):
|
||||
class ModelLoadRequest(BaseModel):
|
||||
name: str
|
||||
max_seq_len: Optional[int] = 4096
|
||||
gpu_split: Optional[str] = "auto"
|
||||
gpu_split_auto: Optional[bool] = True
|
||||
gpu_split: Optional[List[float]] = Field(default_factory=list)
|
||||
rope_scale: Optional[float] = 1.0
|
||||
rope_alpha: Optional[float] = 1.0
|
||||
no_flash_attention: Optional[bool] = False
|
||||
|
||||
Reference in New Issue
Block a user