vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 15:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

support npu

Browse source
This commit is contained in:
djw 2025-07-21 12:26:14 +00:00
parent dd0e41b3b8
commit 7d51a13c9b
34 changed files with 14004 additions and 5626 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ktransformers/server/args.py
View file

@ -22,6 +22,10 @@ class ArgumentParser:
"--device", type=str, default=self.cfg.model_device, help="Warning: Abandoning this parameter"
)
parser.add_argument("--architectures", type=str, default=self.cfg.model_name)
parser.add_argument("--tp", type=int, default=1)
parser.add_argument("--q4_gguf_path", type=str, default=None)
parser.add_argument("--gguf_path", type=str, default=self.cfg.gguf_path)
parser.add_argument("--optimize_config_path", default=None, type=str, required=False)
parser.add_argument("--cpu_infer", type=int, default=self.cfg.cpu_infer)