Update model_loader deps and qqq quantization deps (#2220) (#2318)

Co-authored-by: HandH1998 <1335248067@qq.com>
This commit is contained in:
Yineng Zhang
2024-12-02 23:22:13 +08:00
committed by GitHub
parent 33deca81b5
commit 85e1a6f3aa
58 changed files with 2363 additions and 366 deletions

View File

@@ -147,9 +147,12 @@ class Scheduler:
self.model_config = ModelConfig(
server_args.model_path,
trust_remote_code=server_args.trust_remote_code,
revision=server_args.revision,
context_length=server_args.context_length,
model_override_args=server_args.json_model_override_args,
is_embedding=server_args.is_embedding,
dtype=server_args.dtype,
quantization=server_args.quantization,
)
self.is_generation = self.model_config.is_generation