Skip to content
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

[Bugfix] Use LoadFormat values as choices for vllm serve --load-format #7784

Merged
merged 1 commit into from
Aug 22, 2024
Merged

[Bugfix] Use LoadFormat values as choices for vllm serve --load-format #7784

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
9 changes: 3 additions & 6 deletions vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,8 @@

import vllm.envs as envs
from vllm.config import (CacheConfig, DecodingConfig, DeviceConfig,
EngineConfig, LoadConfig, LoRAConfig, ModelConfig,
ObservabilityConfig, ParallelConfig,
EngineConfig, LoadConfig, LoadFormat, LoRAConfig,
ModelConfig, ObservabilityConfig, ParallelConfig,
PromptAdapterConfig, SchedulerConfig,
SpeculativeConfig, TokenizerPoolConfig)
from vllm.executor.executor_base import ExecutorBase
Expand Down Expand Up @@ -214,10 +214,7 @@ def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
'--load-format',
type=str,
default=EngineArgs.load_format,
choices=[
'auto', 'pt', 'safetensors', 'npcache', 'dummy', 'tensorizer',
'bitsandbytes'
],
choices=[f.value for f in LoadFormat],
help='The format of the model weights to load.\n\n'
'* "auto" will try to load the weights in the safetensors format '
'and fall back to the pytorch bin format if safetensors format '
Expand Down
Loading