PR #4281 Merge qwen to llama cpp

Merge qwen to llama cpp #4281

ggerganov merged 3 commits into ggml-org:master from merge_qwen_to_llama_cpp

Merge pull request #1 from ggerganov/master

479af499

enable qwen to llama.cpp

60d80856

ggerganov added high priority

ggerganov added model

ggerganov added need feedback

ggerganov commented on 2023-12-01

llama : do not GPU split bias tensors

ad04d174

ggerganov merged 37c746d6 into master 2 years ago

Reviewers

ggerganov

riverzhou

Assignees

No one assigned

Labels

high priority model need feedback

Milestone

No milestone