mirror of
https://github.com/theroyallab/tabbyAPI.git
synced 2026-03-15 00:07:28 +00:00
Dependencies: Change handling of exllamav2 checks
ExllamaV2 should check for solely exllamav2, otherwise errors don't make sense. Migrate the combined "exl2" computed property to "inference" since those are the required dependencies for minimal inference. Signed-off-by: kingbri <bdashore3@proton.me>
This commit is contained in:
@@ -22,7 +22,7 @@ def check_exllama_version():
|
||||
"pip install --upgrade .[amd]\n\n"
|
||||
)
|
||||
|
||||
if not dependencies.exl2:
|
||||
if not dependencies.exllamav2:
|
||||
raise SystemExit(("Exllamav2 is not installed.\n" + install_message))
|
||||
|
||||
required_version = version.parse("0.2.2")
|
||||
|
||||
@@ -15,7 +15,7 @@ from common.networking import handle_request_error
|
||||
from common.tabby_config import config
|
||||
from common.optional_dependencies import dependencies
|
||||
|
||||
if dependencies.exl2:
|
||||
if dependencies.exllamav2:
|
||||
from backends.exllamav2.model import ExllamaV2Container
|
||||
|
||||
# Global model container
|
||||
|
||||
@@ -25,7 +25,7 @@ class DependenciesModel(BaseModel):
|
||||
|
||||
@computed_field
|
||||
@property
|
||||
def exl2(self) -> bool:
|
||||
def inference(self) -> bool:
|
||||
return self.torch and self.exllamav2 and self.flash_attn
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user