[Migration] Migrate GGUF quantization support to plugin (#39612)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
@@ -103,7 +103,6 @@ from vllm.transformers_utils.config import (
|
||||
is_interleaved,
|
||||
maybe_override_with_speculators,
|
||||
)
|
||||
from vllm.transformers_utils.gguf_utils import is_gguf
|
||||
from vllm.transformers_utils.repo_utils import get_model_path
|
||||
from vllm.transformers_utils.utils import is_cloud_storage
|
||||
from vllm.utils.argparse_utils import (
|
||||
@@ -1558,10 +1557,6 @@ class EngineArgs:
|
||||
return engine_args
|
||||
|
||||
def create_model_config(self) -> ModelConfig:
|
||||
# gguf file needs a specific model loader
|
||||
if is_gguf(self.model):
|
||||
self.quantization = self.load_format = "gguf"
|
||||
|
||||
if not envs.VLLM_ENABLE_V1_MULTIPROCESSING:
|
||||
logger.warning(
|
||||
"The global random seed is set to %d. Since "
|
||||
|
||||
Reference in New Issue
Block a user