Support multi-thread model weight loading (#7277)

This commit is contained in:
xianzhiT
2025-06-25 01:39:10 +08:00
committed by GitHub
parent 8ecad0b16f
commit 9f1787fa60
4 changed files with 143 additions and 10 deletions

View File

@@ -547,6 +547,7 @@ class ModelRunner:
self.load_config = LoadConfig(
load_format=self.server_args.load_format,
download_dir=self.server_args.download_dir,
model_loader_extra_config=self.server_args.model_loader_extra_config,
)
if self.server_args.load_format == "gguf":
monkey_patch_vllm_gguf_config()