biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-07-28 10:42:40 +08:00
committed by GitHub
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
vllm/engine/arg_utils.py
View File

@@ -22,14 +22,15 @@ from typing_extensions import TypeIs
import vllm.envs as envs
from vllm.config import (BlockSize, CacheConfig, CacheDType, CompilationConfig,
ConfigFormat, ConfigType, DecodingConfig,
DetailedTraceModules, Device, DeviceConfig,
DistributedExecutorBackend, GuidedDecodingBackend,
GuidedDecodingBackendV1, HfOverrides, KVEventsConfig,
KVTransferConfig, LoadConfig, LogprobsMode,
LoRAConfig, ModelConfig, ModelDType, ModelImpl,
MultiModalConfig, ObservabilityConfig, ParallelConfig,
PoolerConfig, PrefixCachingHashAlgo, SchedulerConfig,
ConfigFormat, ConfigType, ConvertOption,
DecodingConfig, DetailedTraceModules, Device,
DeviceConfig, DistributedExecutorBackend,
GuidedDecodingBackend, GuidedDecodingBackendV1,
HfOverrides, KVEventsConfig, KVTransferConfig,
LoadConfig, LogprobsMode, LoRAConfig, ModelConfig,
ModelDType, ModelImpl, MultiModalConfig,
ObservabilityConfig, ParallelConfig, PoolerConfig,
PrefixCachingHashAlgo, RunnerOption, SchedulerConfig,
SchedulerPolicy, SpeculativeConfig, TaskOption,
TokenizerMode, VllmConfig, get_attr_docs, get_field)
from vllm.logger import init_logger
@@ -270,7 +271,9 @@ class EngineArgs:
str, List[str]]] = ModelConfig.served_model_name
tokenizer: Optional[str] = ModelConfig.tokenizer
hf_config_path: Optional[str] = ModelConfig.hf_config_path
task: TaskOption = ModelConfig.task
runner: RunnerOption = ModelConfig.runner
convert: ConvertOption = ModelConfig.convert
task: Optional[TaskOption] = ModelConfig.task
skip_tokenizer_init: bool = ModelConfig.skip_tokenizer_init
enable_prompt_embeds: bool = ModelConfig.enable_prompt_embeds
tokenizer_mode: TokenizerMode = ModelConfig.tokenizer_mode
@@ -461,7 +464,11 @@ class EngineArgs:
)
if not ('serve' in sys.argv[1:] and '--help' in sys.argv[1:]):
model_group.add_argument("--model", **model_kwargs["model"])
model_group.add_argument("--task", **model_kwargs["task"])
model_group.add_argument("--runner", **model_kwargs["runner"])
model_group.add_argument("--convert", **model_kwargs["convert"])
model_group.add_argument("--task",
**model_kwargs["task"],
deprecated=True)
model_group.add_argument("--tokenizer", **model_kwargs["tokenizer"])
model_group.add_argument("--tokenizer-mode",
**model_kwargs["tokenizer_mode"])
@@ -870,6 +877,8 @@ class EngineArgs:
return ModelConfig(
model=self.model,
hf_config_path=self.hf_config_path,
runner=self.runner,
convert=self.convert,
task=self.task,
tokenizer=self.tokenizer,
tokenizer_mode=self.tokenizer_mode,